Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks173 from public data
- GraRep: Learning Graph Representations with Global Structural Information1,749
A novel model for learning vertex representations of weighted graphs that integrates global structural information of the graph into the learning process and significantly outperforms other state-of-the-art methods in such tasks.
- Deep Neural Networks for Learning Graph Representations1,063
A novel model for learning graph representations, which generates a low-dimensional vector representation for each vertex by capturing the graph structural information directly, and which outperforms other stat-of-the-art models in such tasks.
- Knowing What, How and Why: A Near Complete Solution for Aspect-Based Sentiment Analysis531
This paper introduces a new subtask under ABSA, named aspect sentiment triplet extraction (ASTE), and proposes a two-stage framework to address this task, which outperforms a few strong baselines adapted from state-of-the-art related methods.
- Attention Guided Graph Convolutional Networks for Relation Extraction496
Attention Guided Graph Convolutional Networks is proposed, a novel model which directly takes full dependency trees as inputs and can be understood as a soft-pruning approach that automatically learns how to selectively attend to the relevant sub-structures useful for the relation extraction task.
- Learning Latent Forests for Medical Relation Extraction401
This paper presents a novel method that automatically learns a retrieval model alternately with the programmer from weak supervision alternately with the programmer from weak supervision, i.e., the system’s performance with respect to the produced answers.
- Large language models in health care: Development, applications, and challenges365
It is believed that LLMs may be used widely in preconsultation, diagnosis, and management, with appropriate development and supervision, and hold tremendous promise in assisting with medical education, medical writing and other related applications.
- Position-Aware Tagging for Aspect Sentiment Triplet Extraction339
This work proposes the first end-to-end model with a novel position-aware tagging scheme that is capable of jointly extracting the triplets and results show that jointly capturing elements in the triplet using this approach leads to improved performance over the existing approaches.
- Reasoning with Latent Structure Refinement for Document-Level Relation Extraction332
This work proposes a novel model that empowers the relational reasoning across sentences by automatically inducing the latent document-level graph and develops a refinement strategy, which enables the model to incrementally aggregate relevant information for multi-hop reasoning.
- Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders256
It is argued that it can be beneficial to design two distinct encoders to capture such two different types of information in the learning process, and proposed is the novel {\em table-sequence encoder} where two different encoder -- a table encoder and a sequence encoder are designed to help each other in the representation learning process.
- Joint Mention Extraction and Classification with Mention Hypergraphs241
A novel model is presented for the task of joint mention extraction and classification that is able to effectively capture overlapping mentions with unbounded lengths and can be extended to additionally capture mention heads explicitly in a joint manner under the same time complexity.
- Aligning Cross-Lingual Entities with Multi-Aspect Information189
This work investigates embedding-based approaches to encode entities from multilingual KGs into the same vector space, where equivalent entities are close to each other, and applies graph convolutional networks to combine multi-aspect information of entities to learn entity embeddings.
- Interventional Video Grounding with Dual Contrastive Learning175
A novel paradigm from the perspective of the causal inference, i.e., interventional video grounding (IVG) that leverages backdoor adjustment to deconfound the selection bias based on structured causal model (SCM) and do-calculus P(Y |do(X)).
- Neural Segmental Hypergraphs for Overlapping Mention Recognition171
This work proposes a novel segmental hypergraph representation to model overlapping entity mentions that are prevalent in many practical datasets and shows that the model built on top of such a new representation is able to capture features and interactions that cannot be captured by previous models while maintaining a low time complexity for inference.
- A generative model for parsing natural language to meaning representations158
The generative model is applied to the task of mapping sentences to hierarchical representations of their underlying meaning and achieves state-of-the-art performance when tested on two publicly available corpora.
- Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning149
This work introduces a dense connection strategy, proposing a novel Densely Connected Graph Convolutional Network (DCGCN), able to integrate both local and non-local features to learn a better structural representation of a graph.
- UER: An Open-Source Toolkit for Pre-training Models148
This work proposes an assemble-on-demand pre-training toolkit, namely Universal Encoder Representations (UER), which is loosely coupled, and encapsulated with rich modules, and built a model zoo, which contains pre-trained models based on different corpora, encoders, and targets.
- Better Punctuation Prediction with Dynamic Conditional Random Fields144
Empirical results show that the proposed approach is designed to jointly perform both sentence boundary and sentence type prediction, and punctuation prediction on speech utterances, outperforms an approach based on linear-chain conditional random fields and other previous approaches.
- cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information132
Empirical results show that the proposed cw2vec approach consistently outperforms state-of-the-art approaches such as word-based word2vec and GloVe, character-based CWE, component-based JWE and pixel-based GWE.
- Re-examining the Role of Schema Linking in Text-to-SQL130
This work provides a schema linking corpus based on the Spider text-to-SQL dataset, and builds a simple BERT-based baseline to perform a data-driven study on schema linking, finding when schema linking is done well, SLSQL demonstrates good performance on Spider despite its structural simplicity.
- A Neural Multi-digraph Model for Chinese NER with Gazetteers129
This work proposes a novel approach based on graph neural networks with a multi-digraph structure that captures the information that the gazetteers offer that is effective in incorporating rich gazetteser information while resolving ambiguities, outperforming previous approaches.
- 122
- Dependency-Guided LSTM-CRF for Named Entity Recognition112
This work proposes a simple yet effective dependency-guided LSTM-CRF model to encode the complete dependency trees and capture the above properties for the task of named entity recognition (NER).
- Neural Adaptation Layers for Cross-domain Named Entity Recognition112
This paper proposes lightweight yet effective methods for performing domain adaptation for neural models, which introduce adaptation layers on top of existing neural architectures, where no re-training using the source domain data is required.
- Learning Latent Opinions for Aspect-level Sentiment Classification112
A segmentation attention based LSTM model which can effectively capture the structural dependencies between the target and the sentiment expressions with a linear-chain conditional random field (CRF) layer is proposed.
- A Neural Transition-based Model for Nested Mention Recognition107
This paper introduces a scalable transition-based method to model the nested structure of mentions that gets the state-of-the-art performances in ACE datasets, showing its effectiveness in detecting nested mentions.
- Exploring Task Difficulty for Few-Shot Relation Extraction93
This paper introduces a novel approach based on contrastive learning that learns better representations by exploiting relation label information and designs a method that allows the model to adaptively learn how to focus on hard tasks.
- Better Modeling of Incomplete Annotations for Named Entity Recognition86
This work highlights several pitfalls associated with learning under such a setup in the context of NER and proposes a novel yet easy-to-implement approach for recognizing named entities with incomplete data annotations.
- Understanding Attention for Text Classification85
A study on understanding the internal mechanism of attention by looking into the gradient update process, and proposing to analyze for each word token the following two quantities: its polarity score and its attention score, where the latter is a global assessment on the token's significance.
- Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review72
This work aims to provide the natural language processing (NLP) community with a timely review of backdoor attacks and countermeasures and points out the crucial areas for future research on the backdoor, especially soliciting more efficient and practical countermeasures.
- MalwareTextDB: A Database for Annotated Malware Articles71
An annotation framework is introduced based on the MAEC vocabulary for defining malware characteristics, along with a database consisting of 39 annotated APT reports with a total of 6,819 sentences, which is used to construct models that can potentially help cybersecurity researchers in their data collection and analytics efforts.
- Aspect Sentiment Classification with Aspect-Specific Opinion Spans70
A neat and effective structured attention model by aggregating multiple linear-chain CRFs that allows the model to extract aspect-specific opinion spans and then evaluate sentiment polarity by exploiting the extracted opinion features.
- Learning Latent Sentiment Scopes for Entity-Level Sentiment Analysis66
This paper proposes a novel approach that can explicitly model the latent sentiment scopes within which each named entity is embedded and is able to achieve better results compared to existing approaches based on conventional conditional random fields (CRFs) and a more recent work based on neural networks.
- 64
- 63
- A Probabilistic Forest-to-String Model for Language Generation from Typed Lambda Calculus Expressions61
This paper describes a novel probabilistic approach for generating natural language sentences from their underlying semantics in the form of typed lambda calculus, built on top of a novel reduction-based weighted synchronous context free grammar formalism.
- APE: Argument Pair Extraction from Peer Review and Rebuttal via Multi-task Learning58
This paper introduces a new argument pair extraction (APE) task on peer review and rebuttal in order to study the contents, the structure and the connections between them, and proposes a multitask learning framework based on hierarchical LSTM networks.
- To be Closer: Learning to Link up Aspects with Opinions54
The learning process allows the tree structure to adaptively correlate the aspect and opinion words, enabling the polarity in the ABSA task to be better identified, and the proposed model significantly outperforms recent strong baselines.
- Uncovering Main Causalities for Long-tailed Information Extraction52
The proposed counterfactual IE (CFIE) is a novel framework that aims to uncover the main causalities behind data in the view of causal inference, and introduces a unified structural causal model for various IE tasks, describing the relationships among variables.
- A hybrid approach for measuring semantic similarity based on IC-weighted path distance in WordNet51
A hybrid WordNet-based approach CSSM-ICSP to measuring concept semantic similarity is proposed, which leverage the information content of concepts to weight the shortest path distance between concepts and a novel model of the intrinsic IC of concepts is developed.
- Efficient Dependency-Guided Named Entity Recognition51
This work investigates on how to better utilize the structured information conveyed by dependency trees to improve the performance of NER and shows that certain global structured information of the dependency trees can be exploited when building NER models where such information can provide guided learning and inference.
- Matrix product operators for sequence-to-sequence learning49
A machine learning model is constructed in which matrix product operators are trained to implement sequence to sequence prediction, i.e. given a sequence at a time step, it allows one to predict the next sequence.
- Better Transition-Based AMR Parsing with a Refined Search Space48
This paper proposes to conduct the search in a refined search space based on a new compact AMR graph and an improved oracle, and achieves the state-of-the-art performance on various datasets with minimal additional information.
- A Simple Regularization-based Algorithm for Learning Cross-Domain Word Embeddings48
This paper presents a simple yet effective method for learning word embeddings based on text from different domains and demonstrates the effectiveness of the approach through extensive experiments on various down-stream NLP tasks.
- Better Feature Integration for Named Entity Recognition47
This work proposes a simple and robust solution to incorporate both types of features with the Synergized-LSTM (Syn-L STM), which clearly captures how the two types of feature interact.
- Automatic Event Extraction with Structured Preference Modeling47
A novel sequence labeling model based on the latent-variable semi-Markov conditional random fields for jointly extracting argument roles of events from texts and shows empirically that the structured preferences are crucial to the success of this task.
- Neural Architectures for Multilingual Semantic Parsing44
This paper trains one multilingual model that is capable of parsing natural language sentences from multiple different languages into their corresponding formal semantic representations and extends an existing sequence-to-tree model to a multi-task learning framework which shares the decoder for generating semantic representations.
- DAMO-NLP at SemEval-2022 Task 11: A Knowledge-based System for Multilingual Named Entity Recognition43
- Pre-training for Abstractive Document Summarization by Reinstating Source Text43
Three pre-training objectives are presented which allow us to pre-train a Seq2Seq based abstractive summarization model on unlabeled text and show that all three objectives can improve performance upon baselines.
- Combining Spans into Entities: A Neural Two-Stage Approach for Recognizing Discontiguous Entities42
A neural two-stage approach to recognizing discontiguous and overlapping entities by decomposing this problem into two subtasks, which achieves the state-of-the-art performance in a standard dataset, even in the absence of external features that previous methods used.
- 42
- Text2Math: End-to-end Parsing Text into Math Expressions40
This work proposes Text2Math, a model for semantically parsing text into math expressions that aims to predict the complete math expression at once as a tree structure, where minimal manual efforts are involved in the process.
- 36
- Predicting the Daily 10.7-cm Solar Radio Flux Using the Long Short-Term Memory Method36
The overall prediction accuracy of the LSTM method is equivalent to those of the widely used autoregressive (AR) and backpropagation neural network (BP) models, and especially for 2-day and 3-day forecasts, the L STM model is slightly better.
- 34
- Joint Detection and Location of English Puns32
An approach that addresses pun detection and pun location jointly from a sequence labeling perspective is presented, employing a new tagging scheme such that the model is capable of performing such a joint task, where useful structural information can be properly captured.
- 30
- 30
- SemEval-2018 Task 8: Semantic Extraction from CybersecUrity REports using Natural Language Processing (SecureNLP)30
The world’s largest publicly available dataset of annotated malware reports is introduced in this task, which comprises four SubTasks done incrementally to predict the characteristics of a specific malware using cybersecurity reports.
- Learning Explicit and Implicit Structures for Targeted Sentiment Analysis27
This work argues that both types of information (implicit and explicit structural information) are crucial for building a successful targeted sentiment analysis model and shows that properly capturing both information is able to lead to better performance than competitive existing approaches.
- Improving Word Embeddings with Convolutional Feature Learning and Subword Information27
A convolutional neural network architecture is introduced that allows us to measure structural information of context words and incorporate subword features conveying semantic, syntactic and morphological information related to the words.
- Learning to Capitalize with Character-Level Recurrent Neural Networks: An Empirical Study27
An approach using character-level recurrent neural networks (RNN), which performs competitively compared to language modeling and conditional random fields (CRF) approaches is proposed.
- Learning with Structured Representations for Negation Scope Extraction26
This work reports an empirical study on the task of negation scope extraction given the negation cue, and designs approaches based on conditional random fields, semi-Markov CRF, as well as latent-variable CRF models to capture useful information.
- Unsupervised Galaxy Morphological Visual Representation with Deep Contrastive Learning24
This paper presents an approach, based on contrastive learning, with aim of learning galaxy morphological visual representation using only unlabeled data, and incorporates vision transformers and a convolutional network to provide rich semantic representation via the fusion of multi-hierarchy features.
- Twitter Homophily: Network Based Prediction of User’s Occupation24
This study extends an existing data set for this problem, and achieves significantly better performance by using social network homophily that has not been fully exploited in previous work by using the graph convolutional network to exploit socialhomophily.
- ENT-DESC: Entity Description Generation by Exploring Knowledge Graph23
A large-scale and challenging dataset that involves retrieving abundant knowledge of various types of main entities from a large knowledge graph (KG), which makes the current graph-to-sequence models severely suffer from the problems of information loss and parameter explosion while generating the descriptions.
- 20
- 20
- Neural Chinese Address Parsing20
This paper introduces a new task – Chinese address parsing – the task of mapping Chinese addresses into semantically meaningful chunks, and investigates neural structured prediction models with latent variables to capture such rich structural information within Chinese addresses.
- Topical Coherence in LDA-based Models through Induced Segmentation20
This paper presents an LDA-based model that generates topically coherent segments within documents by jointly segmenting documents and assigning topics to their words, and shows the effectiveness of the model in terms of perplexity, Normalized Pointwise Mutual Information, and the Micro F1 measure for text classification.
- Bucket‐based authentication for outsourced databases20
This paper proposes bucket‐based authentication that can keep data confidentiality and meanwhile guarantee data integrity, and proposes a new approach based on bucket checksum, which can be used for the authentication of multiple tuples at one time.
- Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff19
A new evaluation metric, Golden Transfer within Tolerance (GT-T), is proposed to assess the performance by considering the tolerance property of the MHCH, and a matching inference mechanism is introduced to capture the contextual matching features.
- Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation19
This paper proposes Lightweight Dynamic Graph Convolutional Networks (LDGCNs) that capture richer non-local interactions by synthesizing higher order information from the input graphs and develops two novel parameter saving strategies based on the group graph convolutions and weight tied convolutions to reduce memory usage and model complexity.
- Improving Semantic Parsing with Enriched Synchronous Context-Free Grammar19
This article introduces both structure and syntax informed nonterminals, better guiding the parsing in favor of well-formed structure, instead of using a uninformed nonterminal in SCFGs, and addresses the unknown word translation issue via synthetic translation rules.
- 18
- Semantic Parsing with Neural Hybrid Trees17
By combining the strengths of the exact global inference in the hybrid tree models and the power of neural networks to extract high level features, this model is able to achieve new state-of-the-art results on standard benchmark datasets across different languages.
- A General Regularization Framework for Domain Adaptation17
A domain adaptation framework is proposed, and it is formally proved that it generalizes the feature augmentation technique in and the multi-task regularization framework in and allows practitioners to tune hyper-parameters to encourage transfer between close domains and avoid negative transfer between distant ones.
- 16
- 16
- Semantic Parsing with Relaxed Hybrid Trees15
A novel model for parsing natural language sentences into their formal semantic representations that is able to perform integrated lexicon acquisition and semantic parsing, and defines distributions over the novel relaxed hybrid tree structures which jointly represent both sentences and semantics.
- Constrained Layout Generation with Factor Graphs14
This paper addresses the challenge of object-centric lay-out generation under spatial constraints, seen in multi-ple domains including floorplan design process, with a factor graph based approach with four latent variable nodes for each room, and a factor node for each constraint.
- 14
- WN-Salience: A Corpus of News Articles with Entity Salience Annotations14
A new dataset, the WikiNews Salience dataset (WN-Salience), is presented, which can be used to benchmark tasks such as entity salience detection and salient entity linking and demonstrates that WN- Salience is a challenging testbed that is complementary to existing ones.
- Learning Cross-lingual Distributed Logical Representations for Semantic Parsing13
This work extends two existing monolingual semantic parsers to incorporate such cross-lingual distributed logical representations as features and shows how learning distributed representations of the logical forms from data annotated in different languages can be used for improving the performance of a monolingUAL semantic parser.
- Dependency-based Hybrid Trees for Semantic Parsing12
This work proposes a novel dependency-based hybrid tree model for semantic parsing, which converts natural language utterance into machine interpretable meaning representations and integrates a neural component into the model and proposes an efficient dynamic-programming algorithm to perform tractable inference.
- Constrained Semantic Forests for Improved Discriminative Semantic Parsing12
The model addresses an important limitation associated with the previous state-of-the-art discriminative semantic parsing model – the relaxed hybrid tree model by introducing the authors' constrained semantic forests.
- 12
- 11
- 11
- Quantity Tagger: A Latent-Variable Sequence Labeling Approach to Solving Addition-Subtraction Word Problems11
This work presents a novel approach, Quantity Tagger, that automatically discovers hidden relations among quantities by tagging each quantity with a sign corresponding to one type of mathematical operation.
- Keyphrase Extraction Based on Prior Knowledge11
This paper takes prior knowledge, which contains controlled vocabulary of keyphrases and their prior probability, into consideration to enhance previous methods for keyphrase extraction and achieves competitive performance compared with the state-of-the art methods.
- Semantic Similarity Assessment Using Differential Evolution Algorithm in Continuous Vector Space10
This paper combines corpus-based and WordNet-based similarity methods based on differential evolution (DE) algorithm with a new perspective to estimate lexical semantics and demonstrates that this approach outperforms existing works and conforms more to the human judgement of similarity.
- Data set entity recognition based on distant supervision8
This is the first attempt to apply distant learning to the study of data set entity recognition, and introduces a robust vectorised representation and two data augmentation strategies to address the problem inherent in distant supervised learning methods.
- 8
- Coherent X-rays reveal anomalous molecular diffusion and cage effects in crowded protein solutions7
Anomalous diffusion of ferritin is revealed, linking hydrodynamic and direct interactions to cage-trapping at microsecond time scales, with potential applications for optimizing ferritin-based drug delivery, where protein diffusion is the rate-limiting step.
- Weakly-supervised Audio Temporal Forgery Localization via Progressive Audio-language Co-learning Network7
A progressive audio-language co-learning network (LOCO) that adopts co-learning and self-supervision manners to prompt localization performance under weak supervision scenarios and achieves SOTA performance on three public benchmarks is proposed.
- Semantic Conformance Testing of Relational DBMS7
This work introduces the first method for semantic conformance testing of RDBMSs, formally defining the denotational semantics of SQL and implementing them in Prolog, creating an executable reference RDBMS for differential testing against existing RDBMSs.
- 7
- 7
- 6
- 6
- Learn More Manchu Words with A New Visual-Language Framework6
A visual-language framework, namely the Visual-Language framework for Manchu word Recognition (VLMR), which fuses visual and semantic information to accurately recognize Manchu words.
- WGAN-Based Image Denoising Algorithm6
A network model based on the Wasserstein GAN is proposed to enhance denoising capability of images by the restoration of texture details and noise reduction, and different loss functions are proposed in this paper.
- Spatio-Temporal Event Detection from Multiple Data Sources6
This paper proposes Spatio-Temporal Event Detection (STED), a probabilistic model to discover events, their associated topics, time of occurrence, and the geospatial distribution from multiple data sources, such as news and Twitter.
- 6
- A study on emotional feature recognition in speech6
Three emotional recognition methods based on principal component analysis are introduced and the results show that these method can provide an effective solution to emotional recognition.
- Supervised categorization of JavaScriptTM using program analysis features5
This work has developed a functionality-based categorization of JavaScript, the most widely used web page scripting language, and shows how traditional information retrieval methods can be augmented with the features distilled from the domain knowledge of JavaScript and software analysis to improve classification performance.
- 5
- 4
- 4
- Non-Autoregressive Machine Translation as Constrained HMM4
This paper shows that DAT is essentially a fully connected left-to-right Hidden Markov Model (HMM), and proposes two constrained HMMs: Adaptive Window HMM, which explicitly balances the number of outgoing transitions at different states; and Bi-directional HMM, i.e., a combination of left-to-right and right-to-left HMMs, whose uni-directional components can implicitly regularize each other’s biases via shared parameters.
- 4
- Learning Chinese Word Embeddings By Discovering Inherent Semantic Relevance in Sub-characters4
A tripartite weighted graph is proposed to model the semantic relationship among words, characters, and sub-characters in Chinese word embeddings, in which the semantic relationships are evaluated according to the Chinese linguistic information.
- Semantic Similarity Measurement Using Knowledge-Augmented Multiple-prototype Distributed Word Vector4
This work proposes a knowledge-augmented multiple-prototype model by using corpora and ontologies that append the concept definition and the relational knowledge vector into the target word vector to enrich the semantic information of the word.
- The NUS Statistical Machine Translation System for IWSLT 20094
The system developed by the team of the National University of Singapore for the Chinese-English BTEC task of the IWSLT 2009 evaluation campaign adopted a state-of-the-art phrase-based statistical machine translation approach and focused on experiments with different Chinese word segmentation standards.
- Pet-Bench: Benchmarking the Abilities of Large Language Models as E-Pets in Social Network Services3
PET-BENCH is introduced, a dedicated benchmark that evaluates Large Language Models across both self-interaction and human-interaction dimensions and serves as a foundational resource for benchmarking pet-related LLM abilities and advancing emotionally immersive human-pet interactions.
- Low-resource multi-granularity academic function recognition based on multiple prompt knowledge3
The proposed mix prompt tuning (MPT) provides multi-perspective representations by combining manually designed prompt templates with automatically learned continuous prompt templates to help the given academic function recognition task take full advantage of knowledge in PLMs.
- Minimal Linear Codes Constructed from hierarchical posets with two levels3
This paper uses the geometric method to determine the minimality of linear codes generated by any orders in hierarchical posets with two levels and generalizes their cases of one or two orders to any orders and determines the minimability of the linear codes completely.
- Efficient Model Store and Reuse in an OLML Database System3
A database which stores trained models and reuses these models in a new training task to achieve a better training effect with a small amount of training data is proposed and an efficient model reuse algorithm AdaReuse is developed in the OLML database.
- Cross-Lingual Transfer Learning for Medical Named Entity Recognition3
A new way to obtain medical parallel corpus from medical terminology systems and knowledge bases is found and a methodology which combines cross-lingual language model pretraining and bilingual word embedding alignment with the help of the parallel corpus is proposed.
- Automatic Identification of Research Articles Containing Data Usage Statements3
A bootstrapping-based unsupervised training strategy was able to develop text patterns automatically out of a large training collection of research articles, which were then used to distinguish articles with data use and reuse from those without data usage.
- Investigating Stroke-Level Information for Learning Chinese Word Embeddings.3
This work proposes a novel method for learning Chinese word embeddings that consistently outperforms several state-of-the-art methods, including skipgram, cbow, GloVe and CWE, on the standard word similarity and word analogy tasks.
- Predicting Student Examinee Rate in Massive Open Online Courses3
There does not exist a single classifier that is able to dominate others in all cases, and in many cases, SVN performs the best.
- 3
- 2
- 2
- 2
- Knowledge Graph Empowered Entity Description Generation.2
This paper introduces a large-scale and challenging dataset that involves exploring large knowledge graphs (KG) to retrieve abundant knowledge of various types of main entities, which makes the current graph-to-sequence models severely suffered from the problems of information loss and parameter explosion while generating the description text.
- Slow Feature Analysis for Mitotic Event Recognition2
The slow feature analysis is introduced and a fully-automated mitotic event recognition method for cell populations imaged with time-lapse phase contrast microscopy is proposed, achieving 0.93 area under curve (AUC) and 91% accuracy on a very challenging phase contrast microscopeopy dataset named C2C12.
- Polarization of U.S. Circuit Court Judges: A Machine Learning Approach2
The results show persistent but low partisanship of court opinions in the past century, but whether the partisanship has been increasing over the years is yet to be discussed.
- WHUIR at the NTCIR-12 Temporal Intent Disambiguation Task.2
The overall strategy has been to rely on established off-the-shelf components (e.g., standard classifiers from LIBSVM and natural language processing methods from Stanford CoreNLP) and focus on feature discovering and consider nineteen features in total from query itself.
- 2
- 1
- Identifying Mergers in the Legacy Surveys with Few-shot Learning1
A novel framework utilizing few-shot learning techniques to identify galaxy mergers in the Legacy Surveys, offering a promising avenue for automating the identification of galaxy mergers in large-scale surveys, facilitating the comprehensive study of galaxy evolution and structure formation.
- 1
- 1
- 1
- A Research about the Transmutation Trend of the Silk Road Documentary under Recurrent Neural Network1
Under the circumstances that the national policy on the Silk Road in the next few years is unknown, this paper could better guide the future development trend of this type of documentary creation in the form of modeling, and provide reference for future scholars in this direction.
- 1
- 1
- 1
- STEP: Sequence-to-Sequence Transformer Pre-training for Document Summarization1
STEP (as shorthand for Sequence-to-Sequence Transformer Pre-training), which can be trained on large scale unlabeled documents, is proposed, which is pre-trained using three different tasks, namely sentence reordering, next sentence generation, and masked document generation.
- The Investigation and Research of the Whole Process of Film and TV Making at the Background of Blockchain+1
The technology of blockchain is taken as a tool to investigate and research it, along with the practice in and out of the Labs of Media Art, Digital Media Technology and Virtual&Interactive Art, to see how to execute such a mode like blockchain+film and TV.
- 1
- 1
- The SAS Image Data Classification with Minimum Error Probability Bayes Classifier1
The minimum error probability Bayes classifier is used to solve the problem of separating noise data which obey K distribution from the target which also obeys K, and achieves good results.
- –
- –
- Opening a New Chapter for Computational Linguistics–
This is an opportune moment to reflect on the journal’s legacy, ongoing evolution, and the exciting changes that lie ahead, as the first issue of Volume 51 is launched.
- –
- –
- Recommendation Model Based on Global Intention Learning and Sequence Augmentation–
This paper proposes a recommendation model based on Global Intention Learning and Sequence Augmentation, which efficiently integrates the refined global item association graph into item representations through a self-supervised approach, thereby capturing global collaborative sequence information.
- Interweaving Memories of a Siamese Large Language Model–
This work proposes a model-agnostic PEFT framework, IMSM, which Interweaves Memories of a Siamese Large Language Model, which maintains comparable time and space efficiency to backbone PEFT methods while significantly improving performance and effectively mitigating catastrophic forgetting.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Semantic Similarity Measurement Using Knowledge-Augmented Multiple-prototype Distributed Word Vector–
- –
- –
- Language Processing with Perl and Prolog: Theories, Implemetation, and Application–
A timely, in-depth introduction to the field of NLP using Prolog and, to a lesser extent, Perl, which is suitable for anyone wanting to enter NLP through learning to prototype NLP modules in Prolog.
- The Received Signal Characteristics-Based TOA Estimation in UWB Dense Multipath Channels–
The paper sets the threshold according to the skewness and the maximum slope of the received signal, and then the TOA estimation algorithm outperforms others and detects the FP by calculating the frequencies of TC energy samples in certain frames.
- –
- Momentum Factor Constant Modulus Algorithm and Theory–
Improved algorithm based on momentum factor constant modulus algorithm (MCMA) was studied to solve the problem of slow convergence in blind equalization algorithm, momentum factor was added to the weight vector iteration formula of CMA to improve the convergence speed.
- –
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 2026-10-12. 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.