Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks371 from public data
- ERNIE 2.0: A Continual Pre-Training Framework for Language Understanding914
A continual pre-training framework named ERNIE 2.0 which incrementally builds pre- training tasks and then learns pre-trained models on these constructed tasks via continual multi-task learning is proposed.
- RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering794
This work proposes an optimized training approach, called RocketQA, to improving dense passage retrieval, which significantly outperforms previous state-of-the-art models on both MSMARCO and Natural Questions and demonstrates that the performance of end-to-end QA can be improved based on theRocketQA retriever.
- Geometry-enhanced molecular representation learning for property prediction708
A novel geometry-enhanced molecular representation learning method that uses this geometric data in graph neural networks to predict a range of molecular properties and can considerably outperform various state-of-the-art baselines on different benchmarks.
- Multi-Task Learning for Multiple Language Translation657
The recently proposed neural machine translation model is extended to a multi-task learning framework which shares source language representation and separates the modeling of different target language translation.
- A support vector machine-based ensemble algorithm for breast cancer diagnosis440
The proposed WAUCE model achieves a higher accuracy with a significantly lower variance for breast cancer diagnosis compared to five other ensemble mechanisms and two common ensemble models, i.e., adaptive boosting and bagging classification tree.
- UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning431
A UNIfied-MOdal pre-training architecture, namely UNIMO, which can effectively adapt to both single- modal and multi-modal understanding and generation tasks, and is able to learn more generalizable representations.
- ERNIE-ViL: Knowledge Enhanced Vision-Language Representations through Scene Graphs424
A knowledge-enhanced approach, ERNIE-ViL, which incorporates structured knowledge obtained from scene graphs to learn joint representations of vision-language and ranks the first place on the VCR leaderboard with an absolute improvement of 3.7%.
- 399
- STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework341
A novel prefix-to-prefix framework for si- multaneous translation that implicitly learns to anticipate in a single translation model that achieves low latency and reasonable quality (compared to full-sentence translation) on 4 directions.
- RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking321
A novel joint training approach for dense passage retrieval and passage reranking is proposed, where the dynamic listwise distillation is introduced, where a unified listwise training approach is designed for both the retriever and the re-ranker.
- DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications313
This paper introduces DuReader, a new large-scale, open-domain Chinese machine reading comprehension (MRC) dataset, designed to address real-world MRC, and organizes a shared competition to encourage the exploration of more models.
- SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis299
Sentiment Knowledge Enhanced Pre-training (SKEP) is introduced in order to learn a unified sentiment representation for multiple sentiment analysis tasks, and significantly outperforms strong pre-training baseline, and achieves new state-of-the-art results on most of the test datasets.
- PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable297
This work proposes a novel dialogue generation pre-training framework to support various kinds of conversations, including chit-chat, knowledge grounded dialogues, and conversational question answering, and introduces discrete latent variables to tackle the inherent one-to-many mapping problem in response generation.
- Learning Semantic Hierarchies via Word Embeddings289
This paper proposes a novel and effective method for the construction of semantic hierarchies based on word embeddings, which can be used to measure the semantic relationship between words.
- Towards Conversational Recommendation over Multi-Type Dialogs254
This work creates a human-to-human Chinese dialog dataset DuRecDial, where there are multiple sequential dialogs for a pair of a recommendation seeker and a recommender, where the recommender proactively leads a multi-type dialog to approach recommendation targets and then makes multiple recommendations with rich interaction behavior.
- Pivot language approach for phrase-based statistical machine translation245
This paper proposes a novel method for phrase-based statistical machine translation based on the use of a pivot language, using BLEU as a metric, that significantly outperforms the standard model trained on a small bilingual corpus.
- Rare earth element geochemistry characteristics of seawater and porewater from deep sea in western Pacific238
This study suggests that porewater flux in the western Pacific basin is a minor source of REEs to seawater, and abundant REEs are enriched in sediments, which is mainly caused by the extensive oxic condition, low sedimentation rate and strong adsorption capacity of sediments.
- Progress in Machine Translation225
The history of machine translation is reviewed, including the basic framework and the current dominant framework, Transformer, as well as multilingual translation models to deal with the data sparseness problem and cutting-edge simultaneous translation methods that achieve a balance between translation quality and latency.
- Proactive Human-Machine Conversation with Explicit Conversation Goal219
Experimental results show that dialogue models that plan over the knowledge graph can make full use of related knowledge to generate more diverse multi-turn conversations.
- Cross-lingual Dependency Parsing Based on Distributed Representations201
This paper provides two algorithms for inducing cross-lingual distributed representations of words, which map vocabularies from two different languages into a common vector space and bridges the lexical feature gap by using distributed feature representations and their composition.
- 186
- ConSTGAT177
A spatial-temporal graph neural network that adopts a novel graph attention mechanism, which is designed to fully exploit the joint relations of spatial and temporal information, and a computationally efficient model that applies convolutions over local windows to capture a route's contextual information and further employs multi-task learning to improve the performance.
- End-to-End Speech Translation with Knowledge Distillation177
This paper proposes a knowledge distillation approach to improve end-to-end speech translation model by transferring the knowledge from text translation model throughknowledge distillation.
- 166
- Federated Learning with Class Imbalance Reduction166
An estimation scheme to reveal the class distribution without the awareness of raw data is designed and a multi-arm bandit based algorithm is proposed that can select the client set with minimal class imbalance and can significantly improve the convergence performance of the global model.
- Leveraging Graph to Improve Abstractive Multi-Document Summarization161
A neural abstractive multi-document summarization (MDS) model which can leverage well-known graph representations of documents, to more effectively process multiple input documents and produce abstractive summaries is developed.
- PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning151
To build a high-quality open-domain chatbot, this work introduces the effective training process of PLATO-2 via curriculum learning, achieving new state-of-the-art results.
- Joint Extraction of Entities and Overlapping Relations Using Position-Attentive Sequence Labeling143
A novel unified joint extraction model which directly tags entity and relation labels according to a query word position p, i.e., detecting entity at p, and identifying entities at other positions that have relationship with the former.
- ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation138
An enhanced multi-flow sequence to sequence pre-training and fine-tuning framework named ERNIE-GEN, which bridges the discrepancy between training and inference with an infilling generation mechanism and a noise-aware generation method to make generation closer to human writing patterns.
- Early Cambrian metazoan fossil record of South China: Generic diversity and radiation patterns133
The observed regional biodiversity through this interval has both evolutionary and taphonomic influences: the decline in SSF diversity beginning in the upper Meishucunian was not only related to the decimation of SSFs, but also to a reduction in phosphogenesis.
- Revisiting Embedding Features for Simple Semi-supervised Learning127
Experiments on the task of named entity recognition show that each of the proposed approaches can better utilize the word embedding features, among which the distributional prototype approach performs the best.
- Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification125
An end-to-end neural model is proposed that enables answer candidates from different passages to verify each other based on their content representations and achieves the state-of-the-art performance on the English MS-MARCO dataset and the Chinese DuReader dataset.
- Improved Neural Machine Translation with SMT Features125
The proposed method significantly improves the translation quality of the state-ofthe-art NMT system on Chinese-to-English translation tasks and incorporates statistical machine translation (SMT) features, such as a translation model and an n-gram language model, with the NMT model under the log-linear framework.
- ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora123
This paper proposes Ernie-M, a new training method that encourages the model to align the representation of multiple languages with monolingual corpora, to overcome the constraint that the parallel corpus size places on the model performance.
- 113
- Understanding the Impact of the COVID-19 Pandemic on Transportation-related Behaviors with Human Mobility Data112
The huge amount of human mobility data collected from Baidu Maps, a widely-used Web mapping service in China, is used to look into the detail reaction of the people there during the COVID-19 pandemic, to provide more targeted anti-epidemic measures.
- Domain adaptation for statistical machine translation with domain dictionary and monolingual corpora112
This method first uses out-of-domain corpora to train a baseline system and then uses in-domain translation dictionaries and in- domain monolingual corpora in a unified framework to improve the in- domains performance.
- Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs104
This work proposes a knowledge aware chatting machine with three components, an augmented knowledge graph with both triples and texts, knowledge selector, and knowledge aware response generator, and improves a state of the art reasoning algorithm with machine reading comprehension technology for knowledge selection on the graph.
- Multi-task Attention-based Neural Networks for Implicit Discourse Relationship Representation and Identification103
A novel multi-task attention based neural network model to address implicit discourse relationship representation and identification through two types of representation learning and a multi- task framework for learning knowledge from annotated and unannotated corpora is presented.
- Modeling Coherence for Discourse Neural Machine Translation95
This paper proposes to use discourse context and reward to refine the translation quality from the discourse perspective, and generates the translation of individual sentences at first and trains the model to learn the policy that produces discourse coherent text by a reward teacher.
- A Representation Learning Framework for Multi-Source Transfer Parsing93
This work presents a novel representation learning framework that allows multi-source transfer parsing using full lexical features straightforwardly and significantly outperforms the state-of-the-art transfer system proposed most recently.
- Correcting Chinese Spelling Errors with Phonetic Pre-training89
A novel end-to-end CSC model that integrates phonetic features into language model by leveraging the powerful pre-training and tuning method is proposed and achievesSignificant improvements on SIGHAN datasets and outperforms the previous state-of-the-art methods.
- DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation88
Experimental results show that the use of additional English data can bring performance improvement for Chinese conversational recommendation, indicating the benefits of DuRecDial 2.0.
- Pivot Approach for Extracting Paraphrase Patterns from Bilingual Corpora86
A loglinear model is proposed to compute the paraphrase likelihood of two patterns and exploit feature functions based on maximum likelihood estimation (MLE) and lexical weighting (LW) to extract paraphrase patterns from bilingual parallel corpora.
- 85
- Learning Sense-specific Word Embeddings By Exploiting Bilingual Resources79
This paper addresses the problem of representing words with multiple and sense-specific embeddings, which are learned from bilingual parallel data by representing each word with a single embedding, which fails to capture polysemy.
- Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding74
A novel interactive attention mechanism is proposed which enables ASR and ST to perform synchronously and interactively in a single model and can outperform strong baselines on the quality of speech translation and achieve better speech recognition performances as well.
- A dynamic gradient boosting machine using genetic optimizer for practical breast cancer prognosis74
The proposed GAOGB model demonstrates potential for practical incremental breast cancer prognosis, promising a combination of training effectiveness and efficiency, and validates the impact of parameter, adaptiveness and convergence in devising practical online learning algorithms.
- DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset72
This paper presents DuSQL, a larges-scale and pragmatic Chinese dataset for the cross-domain text-to-SQL task, containing 200 databases, 813 tables, and 23,797 question/SQL pairs, and adopts an effective data construction framework via human-computer collaboration.
- Link Prediction on N-ary Relational Facts: A Graph-based Approach71
The key to the approach is to represent the n-ary structure of a fact as a small heterogeneous graph, and model this graph with edge-biased fully-connected attention, which can more effectively capture associations therein.
- Knowledge Graph Grounded Goal Planning for Open-Domain Conversation Generation70
Experiments demonstrate that the proposed three-layer Knowledge aware Hierarchical Reinforcement Learning based Model outperforms state of the art baselines in terms of user-interest consistency, dialog coherence, and knowledge accuracy.
- Taxonomy and evolution of earliest Ordovician graptoloids70
Rhabdinopora is analysed in terms of population systematics and is envisaged as a diverse complex of intergrading populations that change in time (stratigraphic subspecies) and in ecological space (ecological subspecies).
- Revisiting pivot language approach for machine translation69
A hybrid method combining RBMT and SMT systems to fill up the data gap for pivot translation, where the source-pivot and pivot-target corpora are independent, and a system combination approach to select better translations from those produced by various pivot translation methods.
- 67
- ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval66
A novel distillation method is proposed that significantly advances cross-architecture distillation for dual-encoders and outperforms strong baselines and establishes a new state-of-the-art on open-domain QA benchmarks.
- 65
- ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps64
ERNIE-GeoL is elaborately designed to learn a universal representation of geography-language by pre-training on large-scale data generated from a heterogeneous graph that contains abundant geographic knowledge and demonstrates that ERNIE- GeoL can serve as a fundamental backbone for a wide range of geo-related tasks.
- 62
- 62
- HelixADMET: a robust and endpoint extensible ADMET system incorporating self-supervised knowledge transfer60
H-ADMET is a robust and endpoint extensible ADMET system that incorporates the concept of self-supervised learning to produce a robust pre-trained model that can be fine-tuned to generate new and customised ADMET endpoints, meeting various demands of drug research and development requirements.
- Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data59
An improved statistical model for ancient Chinese texts is designed, and it is shown that this approach has advantage in processing domain-specific text without the support of dictionaries or annotated corpora.
- Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation58
This work presents a novel CG grounded policy learning framework that conducts dialog flow planning by graph traversal, which learns to identify a what-vertex and a how- Vertex from the CG at each turn to guide response generation.
- Automatically Generating Questions from Queries for Community-based Question Answering58
Experimental results show that, the precision of 1-best and 5best generated questions is 67% and 61%, respectively, which outperforms a baseline method that directly retrieves questions for queries in a cQA site search engine.
- BASS: Boosting Abstractive Summarization with Unified Semantic Graph54
BASS is presented, a novel framework for Boosting Abstractive Summarization based on a unified Semantic graph, which aggregates co-referent phrases distributing across a long range of context and conveys rich relations between phrases.
- Learning Adaptive Segmentation Policy for Simultaneous Translation53
A novel adaptive segmentation policy is proposed for simultaneous translation of ASR output that learns to segment the source text by considering possible translations produced by the translation model, maintaining consistency between the segmentation and translation.
- Translation Model Adaptation for Statistical Machine Translation with Monolingual Topic Information53
This paper proposes a novel approach for translation model adaptation by utilizing in-domain monolingual topic information instead of the in- domain bilingual corpora, which incorporates the topic information into translation probability estimation.
- 52
- 48
- Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing47
Experiments on three cross-domain datasets show that the proposed data augmentation framework can consistently improve performance over strong baselines, and the hierarchical generation component is the key for the improvement.
- HGAMN: Heterogeneous Graph Attention Matching Network for Multilingual POI Retrieval at Baidu Maps47
A heterogeneous graph that contains two types of nodes: POI node and query node using the search logs of Baidu Maps is constructed and an attention-based network is developed to jointly learn node representations of the heterogeneousgraph and further design a cross-attention module to fuse the representations of both type of nodes for query-POI relevance scoring.
- Baidu Neural Machine Translation Systems for WMT1946
The systems Baidu submitted for the WMT19 shared task on Chinese<->English news translation are introduced, based on the Transformer architecture with some effective improvements.
- Leveraging multiple mt engines for paraphrase generation46
A method that leverages multiple machine translation (MT) engines for paraphrase generation (PG) using a multi-pivot approach and two kinds of techniques, namely the selection-based and decoding-based techniques, to produce a best paraphrase T for S using the candidates acquired in the first stage.
- ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding45
ERNIE-Gram is proposed, an explicitly n-gram masking method to enhance the integration of coarse-grained information into pre-training and outperforms previous pre- training models like XLNet and RoBERTa by a large margin, and achieves comparable results with state-of-the-art methods.
- 44
- SSML: Self-Supervised Meta-Learner for En Route Travel Time Estimation at Baidu Maps42
This work proposes a novel model-based meta-learning approach, called SSML, to learn the meta-knowledge so as to fast adapt to a user's driving preference and improve the time estimation of the remaining route.
- BSTC: A Large-Scale Chinese-English Speech Translation Dataset42
A large-scale Chinese-English speech translation dataset constructed based on a collection of licensed videos of talks or lectures, including about 68 hours of Mandarin data, their manual transcripts and translations into English, as well as automated transcripts by an automatic speech recognition (ASR) model.
- Treebank-based acquisition of LFG resources for Chinese41
A method to automatically acquire wide-coverage, robust, probabilistic Lexical-Functional Grammar resources for Chinese from the Penn Chinese Treebank, and develops a novel treebank-based approach to recovering non-local dependencies (NLDs) for Chinese parser output.
- Policy Learning for Domain Selection in an Extensible Multi-domain Spoken Dialogue System38
The experimental results suggest that the proposed model marginally outperforms a non-trivial baseline and it is shown that by using a model parameter tying trick, the extensibility of the system can be preserved, where dialogue components in new domains can be easily plugged in, without re-training the domain selection policy.
- Dependency-based n-gram models for general purpose sentence realisation37
This work linearises unordered dependencies in input representations directly rather than via the application of grammar rules, as in traditional chart-based generators, for general-purpose, wide-coverage, probabilistic sentence realisation.
- 36
- 35
- Collocation extraction using monolingual word alignment method34
Compared with previous approaches, which use association measures to extract collocations from the co-occurring word pairs within a given window, this method achieves higher precision and recall.
- Learning to Select External Knowledge With Multi-Scale Negative Sampling33
This work has explored several advanced techniques to enhance the utilization of external knowledge and boost the quality of response generation, including schema guided knowledge decision, negatives enhanced knowledge selection, and knowledge grounded response generation.
- A Universal Framework for Inductive Transfer Parsing across Multi-typed Treebanks33
This paper presents a universal framework for transfer parsing across multi-typed treebanks with deep multi-task learning and considers two kinds of treebanks as source: the multilingual universal treebanks and the monolingual heterogeneous treebanks.
- Improving Entity Recommendation with Search Log and Multi-Task Learning32
The experimental results show that incorporating context information significantly improves entity recommendation, and learning the model in a multi-task learning setting where the query representation is shared across entity recommendation and context-aware ranking could bring further improvements.
- Is Discourse Role Important for Emotion Recognition in Conversation?31
A novel method to exploit latent discourse role information of an utterance to determine the emotion it conveys in a conversation is proposed, using a variant of the Variational-Autoencoder to model the context-aware latent discourse roles of each utterance in an unsupervised way.
- STACL: Simultaneous Translation with Integrated Anticipation and Controllable Latency31
A very simple yet surprisingly effective `wait-k' model trained to generate the target sentence concurrently with the source sentence, but always k words behind, for any given k, is introduced.
- Semantic Similarity Computing Model Based on Multi Model Fine-Grained Nonlinear Fusion29
The combination of the traditional statistical method and deep learning model as well as a novel model based on multi model nonlinear fusion are proposed, which reduces the granularity of feature extraction, so it can grasp the sentence features globally.
- 29
- Extracting paraphrase patterns from bilingual parallel corpora29
A pivot approach for extracting paraphrase patterns from bilingual parallel corpora is presented, whereby the paraphrase patterns in English are extracted using the patterns in another language as pivots, which significantly outperforms a well-known method called discovery of inference rules from text (DIRT).
- SgSum:Transforming Multi-document Summarization into Sub-graph Selection28
A novel MDS framework (SgSum) is proposed to formulate the MDS task as a sub- graph selection problem, in which source documents are regarded as a relation graph of sentences and the candidate summaries are its sub-graphs.
- Learning Adaptive Segmentation Policy for End-to-End Simultaneous Translation27
Inspired by human interpreters, the policy learns to segment the source streaming speech into meaningful units by considering both acoustic features and translation history, maintaining consistency between the segmentation and translation.
- DuETA: Traffic Congestion Propagation Pattern Modeling via Efficient Graph Learning for ETA Prediction at Baidu Maps27
A congestion-sensitive graph based on the correlations of traffic patterns is constructed, and a route-aware graph transformer is developed to directly learn the long-distance correlations of the road segments in order to improve ETA performance.
- 27
- Learning to Recommend Related Entities With Serendipity for Web Search Users27
A learning to recommend framework that consists of two components: related entity finding and candidate entity ranking is proposed that significantly outperforms several strong baseline methods and can significantly improve user engagement against multiple baseline methods.
- Discovering Dialog Structure Graph for Coherent Dialog Generation25
An unsupervised model is presented, Discrete Variational Auto-Encoder with Graph Neural Network (DVAE-GNN), to discover discrete hierarchical latent dialog states and their transitions from corpus as a dialog structure graph, and the use of dialog structure as background knowledge can significantly improve multi-turn coherence.
- 25
- A Unified Architecture for Semantic Role Labeling and Relation Classification25
A unified neural architecture for identifying and classifying multi-typed semantic relations between words in a sentence is described and it is shown that the two tasks can be effectively connected and modeled using a general architecture.
- Exploiting heterogeneous treebanks for parsing25
This work proposes to employ an iteratively trained target grammar parser to perform grammar formalism conversion, eliminating predefined heuristic rules as required in previous methods, and provides two strategies to refine conversion results, and adopts a corpus weighting technique for parsing on homogeneous treebanks.
- Dependency based Chinese sentence realization25
This paper describes log-linear models for a general-purpose sentence realizer based on dependency structures that provides simplicity, efficiency and competitive accuracy.
- Boosting statistical word alignment using labeled and unlabeled data25
This paper modifies the supervised boosting algorithm to a semi-supervised learning algorithm by incorporating the unlabeled data, and investigates two boosting methods for word alignment.
- Personalized Prefix Embedding for POI Auto-Completion in the Search Engine of Baidu Maps24
An end-to-end neural-based framework for POI-AC, which has been recently deployed in the search engine of Baidu Maps, and is composed of a multi-layer Bi-LSTM network to adapt to personalized prefixes, a CNN-based network to model multi-sourced information on POIs, and a triplet ranking loss function to optimize both personalized prefix embeddings and distributed representations of POIs.
- Paraphrasing with search engine query logs24
Experimental results show that the proposed method is effective, which extracts more than 3.5 million pairs of paraphrases with a precision of over 70% and can be used to generate high-quality paraphrase patterns.
- Word alignment for languages with scarce resources using bilingual corpora of other language pairs24
An approach to improve word alignment for languages with scarce resources using bilingual corpora of other language pairs using a third language L3 to build a word alignment model for two languages even if no bilingual corpus is available in this language pair.
- Towards federated transfer learning in electrocardiogram signal analysis23
This work proposes a method to train classifiers for electrocardiograms, able to deal with data of disparate input dimensions, distributed across different institutions, and able to protect patient privacy, and a simple method for creating federated datasets from any centralized dataset.
- Meta-Learned Spatial-Temporal POI Auto-Completion for the Search Engine at Baidu Maps23
This paper finds that 17.9% of users tend to look for diverse POIs at different times or locations using the same prefix, and establishes an end-to-end spatial-temporal POI-AC (abbr. as ST-PAC) module to replace P3AC at Baidu Maps, confirming that MST-PAC is a practical and robust industrial solution for large-scale POI Search.
- DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications23
This work introduces a real-world Chinese dataset – DuReader_robust – designed to evaluate the MRC models from three aspects: over-sensitivity, over-stability and generalization, and shows that M RC models do not perform well on the challenge test set.
- 22
- Application of Landscape Architecture Design in the Water Conservancy Project of the Coastal City22
The application of landscape architecture design in the water conservancy project mainly includes flood control architecture and reservoir and in the future, landscape architectural design will leap forward to the direction of intelligence and gradually realize comprehensive and whole-process monitoring.
- 22
- Active Learning for Dependency Parsing with Partial Annotation22
This paper is the first to apply a probabilistic model to active learning for dependency parsing, which can provide tree probabilities and dependency marginal probabilities as principled uncertainty metrics, and directly learn parameters from PA based on a forest-based training objective.
- 21
- 21
- The effect of translation quality in MT-based cross-language information retrieval21
Retrieval effectiveness is found to correlate highly with the translation quality of the queries, and dictionary-based degradation is shown to have stronger impact than rule- based degradation in MT-based CLIR.
- Semantic Energy: Detecting LLM Hallucination Beyond Entropy20
Semantic Energy is introduced, a novel uncertainty estimation framework that leverages the inherent confidence of LLMs by operating directly on logits of penultimate layer by combining semantic clustering with a Boltzmann-inspired energy distribution, which better captures uncertainty in cases where semantic entropy fails.
- 20
- Improving Pivot-Based Statistical Machine Translation Using Random Walk20
A novel approach that utilizes a machine learning method to improve pivot-based statistical machine translation (SMT) by utilizing Markov random walks to connect possible translation phrases between source and target language.
- Kalman Filter with Adaptive Covariance Estimation for Carrier Tracking under Weak Signals and Dynamic Conditions19
The proposed adaptive KF carrier tracking method for resisting signal strength fading and high dynamic environments introduces the adaptive factor to adjust the process noise covariance to accommodate the noise statistics in actual variable situations.
- Enhancing Dialog Coherence with Event Graph Grounded Content Planning19
This paper devise a novel multi-policy decision making mechanism to foster a coherent dialog with both appropriate content ordering and high contextual relevance and presents a novel event graph grounded Reinforcement Learning (RL) framework.
- 19
- Improve Statistical Machine Translation with Context-Sensitive Bilingual Semantic Embedding Model19
This work proposes a simple and memory-efficient model for learning bilingual embedding, taking both the source phrase and context around the phrase into account, and shows that the proposed method achieves significant improvements on large-scale Chinese-English translation task.
- Exploring the Causality of End-to-End Autonomous Driving18
This work is the first to unveil the mystery of end-to-end autonomous driving and turn the black box into a white one by developing a strong baseline and a tool for exploring causality in the close-loop simulator CARLA.
- Self-Tuning Process Noise in Variational Bayesian Adaptive Kalman Filter for Target Tracking18
An adaptive process noise covariance (Qk)-based variational Bayesian adaptive Kalman filter (AQ-VBAKF) algorithm, which can improve the self-adaptive ability of the state estimation filter in dynamic conditions and outperforms several existing filtering methods in estimation accuracy, robustness, and computational efficiency.
- 18
- Web page segmentation with structured prediction and its application in web page classification18
A learning algorithm based on the structured output Support Vector Machine framework is developed to determine the feature weights, which is capable to consider the inter-dependency among candidate segmentation boundaries.
- 18
- A Linguistically Inspired Statistical Model for Chinese Punctuation Generation18
A three-tier maximum entropy model incorporating linguistically-motivated features for generating the commonly used Chinese punctuation marks in unpunctuated sentences output by a surface realizer is implemented and significantly outperforms a baseline 5-gram language model.
- 18
- XDailyDialog: A Multilingual Parallel Dialogue Corpus17
This paper provides a multilingual parallel open-domain dialog dataset, XDailyDialog, to enable researchers to explore the challenging task of multilingual and cross-lingual open- domain dialog, and proposes a dialog generation model, kNN-Chat, which has a novel knn-search mechanism to support unified response retrieval for monolingual, multilingual, and cross -lingual dialogue.
- PLATO-KAG: Unsupervised Knowledge-Grounded Conversation via Joint Modeling17
Experimental results on two publicly available datasets validate the superiority of PLATO-KAG (Knowledge-Augmented Generation), an unsupervised learning approach for end-to-end knowledge-grounded conversation modeling.
- D-NET: A Pre-Training and Fine-Tuning Framework for Improving the Generalization of Machine Reading Comprehension17
A simple system Baidu submitted for MRQA (Machine Reading for Question Answering) 2019 Shared Task that focused on generalization of machine reading comprehension (MRC) models is introduced, built on a framework of pretraining and fine-tuning, namely D-NET.
- Knowledge Aware Conversation Generation with Reasoning on Augmented Graph.17
This work proposes a knowledge aware chatting machine with three components, augmented knowledge graph containing both factoid and non-factoid knowledge, knowledge selector, and response generator, and demonstrates that supported by such unified knowledge and knowledge selection method, the system can generate more appropriate and informative responses than baselines.
- Improving Statistical Machine Translation with Monolingual Collocation17
The experimental results show that the monolingual collocation probabilities made use in this paper improves the performance of both word alignment and translation quality significantly.
- Example-based machine translation based on tree–string correspondence and statistical generation17
Experimental results indicate that the performance of the example-based machine translation (EBMT) method is comparable with phrase-based statistical MT systems.
- An equivalent pseudoword solution to Chinese word sense disambiguation17
This paper presents a new approach based on Equivalent Pseudowords (EPs) to tackle Word Sense Disambiguation (WSD) in Chinese language and verifies the value of EP for unsupervised WSD.
- Improving Domain-Specific Word Alignment with a General Bilingual Corpus17
This paper proposes an approach to improve word alignment in a specific domain, in which only a small-scale domain-specific corpus is available, by adapting the word alignment information in the general domain to the specific domain.
- A brain MRI dataset and baseline evaluations for tumor recurrence prediction after Gamma Knife radiotherapy16
A baseline framework based on a convolutional neural network is proposed companionably with basic evaluations and will contribute to the future development of automated brain tumor recurrence prediction algorithms and promote the clinical implementations associated with the computer vision field.
- 16
- 16
- 16
- 16
- Learning to Explain Entity Relationships by Pairwise Ranking with Convolutional Neural Networks16
A pairwise ranking model which employs a convolutional neural network to automatically learn relevant features and can be easily trained with backpropagation to perform the ranking task.
- DuMapper: Towards Automatic Verification of Large-Scale POIs with Street Views at Baidu Maps15
This paper proposes DuMapper II, a highly efficient framework to accelerate POI verification by means of deep multimodal embedding and approximate nearest neighbor (ANN) search, which takes the signboard image and the coordinates of a real-world place as input to generate a low-dimensional vector, which can be leveraged by ANN algorithms to conduct a more accurate search through billions of archived POIs in the database within milliseconds.
- 15
- Mixup Decoding for Diverse Machine Translation15
This work proposes a novel method, MixDiversity, to generate different translations for the input sentence by linearly interpolating it with different sentence pairs sampled from the training corpus when decoding, which substantially outperforms all previous diverse machine translation methods.
- GEDIT15
A Geographic-Enhanced and Dependency-guIded sequence Tagging (GEDIT) model to concurrently address the two challenges of newly-coined words and a neural sequence tagging model by integrating and feeding the previously pre-learned representations into a CRF layer.
- Multi-Task Learning for Entity Recommendation and Document Ranking in Web Search15
A multi-task learning framework with deep neural networks (DNNs) to jointly learn and optimize two companion tasks in Web search engines: entity recommendation and document ranking, which can be easily trained in an end-to-end manner.
- 15
- Improving Pivot-Based Statistical Machine Translation by Pivoting the Co-occurrence Count of Phrase Pairs15
This paper presents a novel approach to calculate the translation probability by pivoting the co-occurrence count of source-pivot and pivot-target phrase pairs, and shows that this method leads to significant improvements over the baseline systems.
- 14
- 14
- DuARUS: Automatic Geo-object Change Detection with Street-view Imagery for Updating Road Database at Baidu Maps14
This paper proposes a novel framework called DuARUS for automatic geo-object change detection with street-view imagery, and proposes a two-stage, integrated localization algorithm based on image matching and monocular depth estimation to achieve automatic change detection.
- DuIVA: An Intelligent Voice Assistant for Hands-free and Eyes-free Voice Interaction with the Baidu Maps App14
DuIVA is designed to enable users to control the functionalities of Baidu Maps through voice interaction, rather than visual-manual interaction, which minimizes driver distraction and promotes safe driving by allowing the driver to keep "eyes on the road and hands on the wheel'' while interacting with the BaidU Maps app.
- ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention14
Experimental results demonstrate that ERNIE-Sparse significantly outperforms a variety of strong baseline methods including the dense attention and other efficient sparse attention methods and achieves improvements on classification benchmark and on QA downstream tasks.
- 14
- Personalized Query Auto-Completion for Large-Scale POI Search at Baidu Maps14
The industrial solution to the personalized QAC for the point of interest (POI) search at Baidu Maps makes a good tradeoff between the offline effectiveness of a novel neural learning model that is devised and the online efficiency of an off-the-shelf learning to rank (LTR) approach for the real-time suggestion.
- A Distributed Representation-Based Framework for Cross-Lingual Transfer Parsing14
This paper provides two algorithms for inducing cross-lingual distributed representations of words, which map vocabularies from two different languages into a common vector space and significantly outperforms state-of-the-art delexicalized models augmented with projected cluster features on identical data.
- The TCH Machine Translation System for IWSLT 200814
This paper reports on the first participation of TCH (Toshiba (China) Research and Development Center) at the IWSLT evaluation campaign and improves each module in the MT systems as follows for better performance of MT.
- Multi-agent Learning for Neural Machine Translation13
Experimental results on NIST Chinese-English, IWSLT 2014 German- English, WMT 2014 English-German and large-scale Chinese- English translation tasks indicate that the approach achieves absolute improvements over the strong baseline sys- tems and shows competitive performance on all tasks.
- Learning a unified embedding space of web search from large-scale query log13
This paper develops the well-known Word2vec to perform the learning of the semantic space with search session data, and uses a set of session graphs to represent search sessions, and the space learning task is cast as a vector learning problem for the graph vertices by maximizing the log-likelihood of a training session data set.
- 13
- Towards Zero-Shot Persona Dialogue Generation with In-Context Learning12
This work first pre-train a persona-augmented dialogue generation model and then utilize in-context prompting mechanism to realize zero-shot persona customization, demonstrating that this method can dramatically improve persona consistency without compromising coherence and informativeness in zero-shot settings.
- 12
- Understanding the Collective Responses of Populations to the COVID-19 Pandemic in Mainland China12
This work confirms the strong correlation between the local pandemic situation in every major Chinese city and the population inflows from Wuhan between 1 January and 23 January 2020, and shows that well-informed individuals are likely to travel less, even while the overall travel demands are low compared to the historical records.
- Towards a Next-Generation Search Engine12
The system architecture of a next-generation search engine that is built with a goal to provide accurate search result on frequently asked concepts, natural language user interface, accurate search results, and interactive user interface and multimedia content retrieval is described.
- DuTraffic: Live Traffic Condition Prediction with Trajectory Data and Street Views at Baidu Maps11
This paper presents DuTraffic, which is a robust and production-ready solution for live traffic condition prediction by taking both trajectory data and street views into account, and proposes a spatial-temporal-based module, TRST-Net, to learn the latent trajectory representation.
- 11
- 11
- An Investigation of Containment Measures Against the COVID-19 Pandemic in Mainland China11
It is confirmed that, although the cities with high GDP per capita attract more inflows from Wuhan, people are more likely to conduct the quarantine measure and to reduce travelling to other cities, and that well-informed individuals are likely to carry out containment measures.
- 11
- Recovering Non-Local Dependencies for Chinese11
This paper surveys non-local dependency constructions in Chinese as represented in the Penn Chinese Treebank and provides an approach for generating proper predicate-argument-modifier structures including NLDs from surface contextfree phrase structure trees.
- 11
- Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation10
This paper presents a systematic investigation of the intrinsic mechanisms by which LLMs integrate internal (parametric) and external (retrieved) knowledge in RAG scenarios, and employs knowledge stream analysis at the macroscopic level and investigates the function of individual modules at the microscopic level.
- PLATO-Ad: A Unified Advertisement Text Generation Framework with Multi-Task Prompt Learning10
A novel unified text ad generation framework with multi-task prompt learning, called PLATO-Ad, to tackle the low-resource ad generation problem and significantly outperforms the state-of-the-art on both offline and online metrics.
- 10
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- Enriching SMT Training Data via Paraphrasing9
This paper proposes a novel method to resolve the coverage problem of SMT system by employing an object function, named Sentence Novelty, to select paraphrases which having the most novel information to the bilingual training corpus of the SMT model.
- 9
- 8
- 8
- Multi-objective parallel robotic dispensing planogram optimisation using association rule mining and evolutionary algorithms8
Four evolutionary algorithms are applied to solve the proposed planogram optimisation model for robotic dispensing systems (RDSs) in mail-order pharmacy automation (MOPA) facilities and the best algorithm with higher performance is identified for each criterion.
- Generating recommendation evidence using translation model8
A statistical model consisting of four sub-models to generate evidences for entities is proposed, which can help users better understand each recommended entity, and figure out the connections between the recommended entities and a given query.
- Generalization of Words for Chinese Dependency Parsing8
Experiments show that the combinations of features from CPOS-tags, POS-tags, and NLMWE-based word classes yield the best un-labelled attachment scores (UASs) and this method is significantly better than three well known open-source dependency parsers.
- Reordering with Source Language Collocations8
A novel reordering model for statistical machine translation (SMT) by means of modeling the translation orders of the source language collocations, learned from a word-aligned bilingual corpus where the collocated words in source sentences are automatically detected.
- Prediction of maximal projection for semantic role labeling8
This paper makes a new definition of MP in S-structure and proposes two methods to predict it: the anchor group approach and the single anchor approach and results indicate that the prediction of MP improves semantic role labeling.
- 8
- Docking-based Virtual Screening with Multi-Task Learning7
The results demonstrate that multi-task learning is a promising machine learning approach for docking-based virtual screening and accelerating the process of drug discovery.
- Reading Customer Reviews to Answer Product-related Questions7
An end-to-end neural architecture directly fed by the raw text of product-related questions and customer reviews to predict the answers and teaches machines to generate and to synthesize multiple question-aware review representations in a reading comprehension fashion to make the decision.
- Two-Word Collocation Extraction Using Monolingual Word Alignment Method7
This article adapts the bilingual word alignment algorithm into a monolingual scenario to extract collocations from monolingUAL corpus, based on the fact that the words in a collocation tend to co-occur in similar contexts as in bilingualword alignment.
- Using RBMT Systems to Produce Bilingual Corpus for SMT7
This paper uses the existing RBMT system to translate the monolingual corpus into synthetic bilingual corpus, which will be used as training data for the Statistical Machine Translation (SMT) system.
- Improving Statistical Word Alignment with Ensemble Methods7
Experimental results indicate that both bagging and cross-validation committees improve the word alignment results regardless of weighted voting or unweighted voting.
- 7
- DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models6
A comprehensive evaluation should be conducted on natural texts, which takes into account the fine-grained linguistic capabilities of QM models, and the detailed breakdown of evaluation by the linguistic phenomena in DuQM helps to diagnose the strength and weakness of different models.
- Evolutionary Game-Theoretical Analysis for General Multiplayer Asymmetric Games6
The gap between heuristic payoff table and dynamic analysis without any in- accuracy is closed and a general framework for m versus n 2-population multiplayer asymmetric games is proposed.
- 6
- DuReaderrobust: A Chinese Dataset Towards Evaluating the Robustness of Machine Reading Comprehension Models.6
The experimental results show that MRC models based on the pre-trained language models perform much worse than human does on the robustness test set, although they perform as well as human on in-domain test set.
- PassGrid: Towards Graph-Supplemented Textual Shoulder Surfing Resistant Authentication6
This work proposes a graph-supplemented textual shoulder surfing resistant authentication system, called PassGrid, which prevents attackers from guessing the passwords even with the help of a camera, and can achieve good performance regarding security and usability.
- Research on the Mixed-Learning Model and the Innovative Talent Cultivation Mechanism Based on Computational Thinking6
This chapter analyzes learning processes and the effects of learning for participants taking basic computer courses at university, and analyzes the validity and feasibility of a hybrid learning model, based on computational thinking.
- Exploiting Collective Hidden Structures in Webpage Titles for Open Domain Entity Extraction6
A novel method for open domain named entity extraction by exploiting the collective hidden structures in webpage titles that uncovers the hidden textual structures shared by sets of webpage titles based on generalized URL patterns and a multiple sequence alignment technique.
- Opening Machine Translation Black Box for Cross-Language Information Retrieval6
This study demonstrates the usefulness of opening the black box of SMT to produce more adequate query translations for CLIR by considering the translation alternatives included in the N-best translation outputs.
- Discriminative pruning of language models for Chinese word segmentation6
This paper presents a discriminative pruning method of n-gram language model for Chinese word segmentation, and proposes a step-by-step growing algorithm to build the language model of desired size.
- 6
- 5
- 5
- 5
- 5
- Utilizing Imbalanced Data and Classification Cost Matrix to Predict Movie Preferences5
The test error among the above-mentioned algorithms that are used to recommend different movie genres are compared and the prediction power is indicated in a comparison of precision and recall with other state-of-the-art recommendation systems.
- 5
- A Method of the Vibration Information Detection for Rotating Machinery Based on the Rolling-Shutter CMOS and Digital Image Processing4
The Random Forest algorithm was identified as the most suitable for fault diagnosis based on vibration information in this work, and achieved the highest diagnostic accuracy, exceeding 98%.
- Towards Boosting Many-to-Many Multilingual Machine Translation with Large Language Models4
It is demonstrated that prompt strategies adopted during finetuning are crucial to zero-shot translation and a cross-lingual consistency regularization is introduced, XConST, to bridge the representation gap among different languages and improve zero-shot translation performance.
- 4
- 4
- PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation4
Compared to the existing state-of-the-art Chinese dialogue model, the overall engagingness of PLATO-K is improved remarkably by 36.
- DuIVRS: A Telephonic Interactive Voice Response System for Large-Scale POI Attribute Acquisition at Baidu Maps4
DuIVRS is designed to proactively acquire POI attributes via a telephonic interactive voice response system, whose tasks are to generate machine-initiative directed dialogues, make scripted telephone calls to businesses, and interact with people who answered the phone to achieve predefined goals through multi-turn dialogues.
- Link the World: Improving Open-domain Conversation with Dynamic Spatiotemporal-aware Knowledge4
Both automatic evaluation and human evaluation show that the proposed new method can improve the effect of open-domain conversation, and the session-level overall score in human evaluation is improved by 59.29% compared with the dialogue pre-training model PLATO-2.
- 4
- 4
- 4
- MONOPOLY: Learning to Price Public Facilities for Revaluing Private Properties with Large-Scale Urban Data4
This paper introduces the newly launched project "Monopoly" (named after a classic board game) in which a distributed approach for revaluing private properties by learning to price public facilities with the large-scale urban data accumulated via Baidu Maps and shows that the approach outperforms several mainstream methods with significant margins.
- Research on Teaching Reform of Computer Course Based on Computational Thinking4
This paper studies and expounds the application of computational thinking in university computer curriculum.
- 4
- 3
- Dual Meta-Learning with Longitudinally Generalized Regularization for One-Shot Brain Tissue Segmentation Across the Human Lifespan3
This paper proposes a dual meta-learning paradigm to learn longitudinally consistent representations and persist when fine-tuning and learns a plug-and-play feature extractor to extract longitudinal-consistent anatomical representations by meta-feature learning and a well-initialized task head for fine- Tuning byMeta-initialization learning.
- 3
- Primary adrenal diffuse large B-cell lymphoma with normal adrenal cortex function: A case report3
R-CHOP is the conventional immunochemotherapy for primary adrenal diffuse large B-cell lymphomas primary to the adrenal gland and the ideal treatment plan remains to be confirmed.
- 3
- 3
- 3
- 3
- 3
- Duer: Intelligent Personal Assistant3
This talk describes Duer, Baidu's intelligent personal assistant, which comprehensively understands people's requirements via multiple channels, including not only explicit utterances, but also user models and rich contexts, and features multi-modal interaction.
- 3
- Bootstrapping Large-scale Named Entities using URL-Text Hybrid Patterns3
A novel method for NE mining using web document titles is proposed to use url-text hybrid patterns that introduce url criterion to better pinpoint high-quality NEs and design a multiclass collaborative learning mechanism in bootstrapping.
- User Behaviors Lend a Helping Hand: Learning Paraphrase Query Patterns from Search Log Sessions3
This paper learns paraphrase patterns from the search log sessions with a classification framework, in which three types of user behavior features are exploited besides the conventional features, to distinguish paraphrases from the simply related queries in the sessions.
- Fuzzy Description Logic F-SHOIQ(G) Supporting Representation of Fuzzy Data Types3
The shortcomings of existing description logics in the representation of fuzzy knowledge and data types are analyzed and a kind of new fuzzy description logic named F-SHOIQ(G) is proposed in the paper, laying a theoretical foundation for the representation and reasoning of fuzzy data information in the Semantic Web.
- Accurate and robust LFG-based generation for Chinese3
Three PCFG-based models for Chinese sentence realisation from Lexical-Functional Grammar f-structures are described and techniques for lexical smoothing and rule smoothing are provided to increase the generation coverage.
- Study on Anti-Virus Engine Based on Heuristic Search of Polymorphic Virus Behavior3
The mechanism of anti-virus engine is discussed and a new method is put forward based on heuristic strategy to avoid being detected by virus scanner that identifies the virus characteristic code.
- 3
- E-commerce Oriented ANS Based on Agent3
An E-commerce ANS based on Agent is proposed, the automated negotiation protocols, negotiation strategies and system architecture of the new ANS are discussed, and the direction of research in the future is figured out.
- 3
- 3
- 3
- Towards few-shot mixed-type dialogue generation2
Experimental results demonstrate that the three key designs — modular-based architecture, prompt-tuning component, and model pre-training — significantly enhance the performance of this framework compared to state-of-the-art baselines.
- Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understanding2
This work proposes Blink, a dynamic visual token resolution framework that emulates the human-inspired process within a single forward pass, and demonstrates its effectiveness in enhancing visual perception and multimodal understanding.
- 2
- GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue2
This study aims to investigate STM models' over-reliance on the edit distance feature, commonly used to measure the semantic similarity of Chinese text pairs, and proposes a novel resampling training strategy called Gradually Learn Samples Containing Superficial Clue (GLS-CSC).
- Towards Multi-Turn Empathetic Dialogs with Positive Emotion Elicitation2
A positive-emotion-guided dialog generation model with a novel loss function design encourages the dialog model to not only elicit positive emotions from users but also ensure smooth emotional transitions along with the whole dialog.
- CLOP: Video-and-Language Pre-Training with Knowledge Regularizations2
This work proposes a Cross-modaL knOwledge-enhanced Pre-training (CLOP) method with Knowledge Regularizations, demonstrating the value of incorporating knowledge regularizations into video-and-language pre-training.
- 2
- 2
- Findings of the Second Workshop on Automatic Simultaneous Translation2
A metric “Monotonic Optimal Sequence” (MOS) is proposed considering both quality and latency to rank the submissions in the AutoSimTrans shared task, and some important open issues in simultaneous translation are discussed.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- Primary bladder diffuse large B-cell lymphoma: A rare case report1
This case highlights that bladder masses may originate from lymphoid tissue, as imaging studies may not reliably distinguish such lesions from cystitis glandularis or adenocarcinoma, as definitive diagnosis requires immunohistochemical confirmation.
- 1
- 1
- 1
- 1
- Coherent Dialog Generation with Query Graph1
This article proposes to leverage a new knowledge source, web search session data, to facilitate hierarchical knowledge sequence planning, which determines a sketch of a multi-turn dialog, and devise a heterogeneous graph neural network to incorporate neighbouring vertex information, or possible future RL action information, into each vertex (as an RL action) representation.
- A Key-Phrase Aware End2end Neural Response Generation Model1
Experimental results show that this model can effectively utilize the key phrase information for semantic association modeling, and it can significantly outperform baseline models in terms of response appropriateness and informativeness.
- Biological Network Modeling Based on Hill Function and Hybrid Evolutionary Algorithm1
Experimental results show that the proposed Hill function-based ordinary differential equation model can infer gene regulatory network more accurately than state of the art methods.
- 1
- Learning a Semantic Space of Web Search via Session Data1
session2vec and session2vec+ models are proposed to learn vectors in the space with search session data, where a search session is regarded as an instantiation of an information need and keeps the interaction information of queries and URLs.
- Transformation from Discontinuous to Continuous Word Alignment Improves Translation Quality1
A weighted vote method is used to transform discontinuous word alignment to continuous alignment, which enables SMT systems extract more phrase pairs, and shows statistically significant improvements of BLEU score in both cases over the baseline systems.
- Bus Transport Transfer Algorithm1
This paper summarizes the algorithm of public transportation optimum route choice of foreign and urban cities, and analyses the realization conditions and influence factors for effective running.
- 1
- Improve SMT Quality with Automatically Extracted Paraphrase Rules1
A novel approach to improve SMT via paraphrase rules which are automatically extracted from the bilingual training data by comparing the source side of the parallel corpus with the target-to-source translations of the target side.
- Web-based Machine Translation1
This talk will introduce the work on web-based machine translation, which involves adapting the MT methods to the web scenario to make better use of the web data and to produce better webbased MT applications.
- Web Knowledge Fusion System Based on Certainty Factor Theory and its Application1
A web knowledge fusion system based on certainty factor theory is proposed, which solves the redundancy and contradiction in the drug subject fusion procedure and provides reliable drug subject information for the online drug supervisory board.
- 1
- 1
- 1
- Design & Implementation of Bidirectional Data Conversion Tool between XPDL and RDB1
The biddirectional data mapping relation and data conversion method between XPDL and RDB are discussed, and a bidirectional data conversion tool that is database platform-independent is analysed.
- 1
- 1
- UTTERANCE SEGMENTATION OF SPOKEN CHINESE1
“dialog turn” and “utterance” are introduced into spoken Chinese analysis and a method of integrating FBSRN with the rules proposed for Chinese utterance segmentation is proposed.
- –
- Track acoustic signal compression method based on sparse decomposition and M 2to1 -guided resampling–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Findings of the Third Workshop on Automatic Simultaneous Translation–
The number of systems submitted this year has increased fourfold compared with last year, and the top 1 ranked system in the speech-to-text track is the first end- to-end submission the task has received in the past three years, which has shown great potential.
- –
- –
- –
- –
- –
- –
- –
- –
- Gene Expression Prediction Based on Hybrid Evolutionary Algorithm–
Results show that ODE based on Hill function could forecast gene expression data more accurately than general ODE model and recurrent neural network.
- –
- –
- Particle Swarm Optimization with Family Communication Strategy–
The experimental results indicated that the proposed FPSO method could improve the convergence performance, and had stronger judgment ability and intelligence than the conventional PSO method.
- –
- –
- –
- –
- –
- –
- –
- An Improved Genetic Algorithm to the Reliability Optimization of Computer Networks–
Experimental results suggest that the proposed optimization approach and application to the reliability of computer networks using improved genetic algorithm is feasible, correct and valid.
- –
- –
- –
- –
- –
- –
- Sentiment classification for online comments based on intuitionistic fuzzy reasoning–
The presented approach employs membership function, non-membership function and hesitant function to depict uncertainties of features, quantitatively, by sample training, as well as sentiment expressions influenced by adverbs of degree, conjunctions and negative words.
- Study on Effect of the Different Biotopes on Growth Status of Wild Hypericum ascyron in Heilongjiang Province–
It was found that species of accompanying plants of wild Hypericum ascyron are related to growing environment, so, fertilizer and water management should be cautioned during cultivation process.
- –
- Introduction to special section on paraphrasing–
This special section of ACM TIST is intended to cover state-of-the-art research in automatic paraphrasing, and includes an approach that uses automatic paraphrase generation to tune parameters for an SMT system based on crowdsourcing.
- A Hierarchical Semantics-Aware Distributional Similarity Scheme–
A hierarchical semanticaware DSS is proposed that exploits semantic relation words as extra context information to guide the similarity calculation and develops relation-based similarities from the distributional similarities among the top-ranked relation words.
- –
- A conversation with Dr. Haifeng Wang–
A complete view of the data is built, the most valuable knowledge is mined from the data, and various products are improved, e.g. the Baidu search engine.
- Report on the first summer school on NLP and IR in Beijing–
The first Summer School on NLP and IR has been organized in China in July 2011 just before SIGIR conference, and this report describes the event.
- Hospital of Wired and Wireless Information Network Fusion Planning Design and Implementation–
Based on the hospital information network status and demand analysis, wired and wireless information network convergence reasonable planning design and achieve, to meet the needs of the existing hospital in each application system on network demand.
- –
- Design of a integrative information management system based on ARM–
A design of a integrative information management system that can realize the whole controlling of the integrative controlling system, based on the high-powered ARM chip LPC2378FBD144, and all parts is all-purpose and extensible.
- –
- –
- Harvesting Related Entities with a Search Engine–
This paper addresses the problem of related entity extraction and focuses on extracting related persons as a case study using q's search results and the query logs containing q to mine candidate related persons for a query person q using a SVM regression model.
- –
- –
- Proceedings of the 23rd International Conference on Computational Linguistics: Tutorial notes: Paraphrases and applications–
It will be shown how paraphrases can help to alleviate data sparseness problem, simplify input sentences, tune parameters, and improve automatic evaluation in statistical MT systems.
- –
- Implementation of Ethernet Communication in Network-based Measurement–
The research and implementation of communication technology in network-based measurement --communication with TCP/IP on ethernet with C-language and UDP client terminal is described.
- –
- –
- –
- –
- –
- Research for Electronic Commerce Pattern Based on Association Rule Mining–
The article proposed ARM base on the ontology (ARMO) with advantages of a clearer summery of the data; fewer rules; Generalization of multilevel, more meaningful result; Multi-level ARM.
- –
- –
- –
- –
- Extensible Storage Structure of Multi-dimensional Data Based on Hierarchy–
The hierarchical cluster CUBE (HCDC) method is introduced which optimizes the efficiency of querying and updating with the hierarchical information, and enables the manipulation of updating of multi-dimension data’s schema.
- Request Dispatch Model Based on Distributed Diagnosis System–
Key technologies for implementing this model, such as CORBA::Any, custom message model, and focus on the ideas of approach and details implementing are discussed.
- –
- –
- Which Campus Network Do We Need in New Century–
The characters and functions and the expectation in the new century of campus network in the future of distance and network teaching are pointed out.
- THE DATABASE RECOVERY STRATEGY IN ORACLE–
This paper gives an introduction to the Oracle′s recovery principles, where failures are grouped and to different groups of failures different recovery techniques are proposed to help database administrators to work out feasible projects for backup and recovery in conformity with different cases.
- –
- How to Establish the Non-disk Network of Windows98–
The characteristics and the basic working principles of the Non-disk Network of PXE-Windows98 are analyzed; the plan of establishing a school computer lab is discussed and the process of how to establish the Network is displayed through practical cases.
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.