Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks148 from public data
- A Diversity-Promoting Objective Function for Neural Conversation Models2,879
This work proposes using Maximum Mutual Information (MMI) as the objective function in neural models, and demonstrates that the proposed MMI models produce more diverse, interesting, and appropriate responses, yielding substantive gains in BLEU scores on two conversational datasets and in human evaluations.
- Deep Reinforcement Learning for Dialogue Generation1,434
This work simulates dialogues between two virtual agents, using policy gradient methods to reward sequences that display three useful conversational properties: informativity, non-repetitive turns, coherence, and ease of answering.
- A Persona-Based Neural Conversation Model1,122
This work presents persona-based models for handling the issue of speaker consistency in neural response generation that yield qualitative performance improvements in both perplexity and BLEU scores over baseline sequence-to-sequence models.
- Adversarial Learning for Neural Dialogue Generation927
This work applies adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances, and investigates models for adversarial evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls.
- Dice Loss for Data-imbalanced NLP Tasks796
This paper proposes to use dice loss in replacement of the standard cross-entropy objective for data-imbalanced NLP tasks, based on the Sørensen--Dice coefficient or Tversky index, which attaches similar importance to false positives and false negatives, and is more immune to the data-IMbalance issue.
- A Unified MRC Framework for Named Entity Recognition709
This paper proposes to formulate the task of NER as a machine reading comprehension (MRC) task, and naturally tackles the entity overlapping issue in nested NER: the extraction of two overlapping entities with different categories requires answering two independent questions.
- A Hierarchical Neural Autoencoder for Paragraphs and Documents618
This paper introduces an LSTM model that hierarchically builds an embedding for a paragraph from embeddings for sentences and words, then decodes this embedding to reconstruct the original paragraph and evaluates the reconstructed paragraph using standard metrics to show that neural models are able to encode texts in a way that preserve syntactic, semantic, and discourse coherence.
- 444
- 399
- Entity-Relation Extraction as Multi-Turn Question Answering395
The proposed multi-turn QA model achieves the best performance on the RESUME dataset, which requires multi-step reasoning to construct entity dependencies, as opposed to the single-step dependency extraction in the triplet exaction in previous datasets.
- Towards a General Rule for Identifying Deceptive Opinion Spam386
This paper explores generalized approaches for identifying online deceptive opinion spam based on a new gold standard dataset, which is comprised of data from three different domains that contains three types of reviews, i.e. customer generated truthful reviews, Turker generated deceptive reviews and employee (domain-expert) generated deception reviews.
- BertGCN: Transductive Text Classification by Combining GNN and BERT329
BertGCN constructs a heterogeneous graph over the dataset and represents documents as nodes using BERT representations and GCN modules within BertGCN, a model that combines large scale pretraining and transductive learning for text classification.
- Text Classification via Large Language Models296
Clue And Reasoning Prompting (CARP) adopts a progressive reasoning strategy tailored to addressing the complex linguistic phenomena involved in text classification, and achieves comparable performances to supervised models with 1,024 examples per class.
- ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information244
This work proposes ChineseBERT, which incorporates both the glyph and pinyin information of Chinese characters into language model pretraining and achieves new SOTA performances on a wide range of Chinese NLP tasks, including machine reading comprehension, natural language inference, text classification, sentence pair matching, and competitive performances in named entity recognition and word segmentation.
- Do Multi-Sense Embeddings Improve Natural Language Understanding?241
A multisense embedding model based on Chinese Restaurant Processes is introduced that achieves state of the art performance on matching human word similarity judgments, and a pipelined architecture for incorporating multi-sense embeddings into language understanding is proposed.
- 224
- Glyce: Glyph-vectors for Chinese Character Representations221
Glyce, the glyph-vectors for Chinese character representations, is presented and it is shown that glyph-based models are able to consistently outperform word/char ID- based models in a wide range of Chinese NLP tasks.
- CorefQA: Coreference Resolution as Query-based Span Prediction198
CorefQA is presented, an accurate and extensible approach for the coreference resolution task, formulated as a span prediction task, like in question answering, which provides the flexibility of retrieving mentions left out at the mention proposal stage.
- Automated known problem diagnosis with event traces188
This work proposes to use system behavior information such as system event traces to build correlations with solved problems, instead of using only vague text descriptions as in existing practices to enable automatic identification of the root cause of a problem if it is a known one, which would further lead to its resolution.
- A Model of Coherence Based on Distributed Sentence Representation162
A neural network model for the coherence task based on distributed sentence representation is introduced, which outperforms existing baselines and generates the state-of-art performance in standard coherence evaluation tasks.
- Recursive Deep Models for Discourse Parsing151
This paper proposes a recursive model for discourse parsing that jointly models distributed representations for clauses, sentences, and entire discourses that obtains comparable performance regarding standard discoursing parsing evaluations when compared against current state-of-art systems.
- Is Word Segmentation Necessary for Deep Learning of Chinese Representations?141
It is shown that word-based models are more vulnerable to data sparsity and the presence of out-of-vocabulary (OOV) words, and thus more prone to overfitting, and this could encourage researchers in the community to rethink the necessity of word segmentation in deep learning-based Chinese Natural Language Processing.
- 116
- Major Life Event Extraction from Twitter based on Congratulations/Condolences Speech Acts115
The feasibility of accurately extracting major life events is demonstrated and the system extracts a fine-grained description of users’ life events based on their published tweets is optimistic that it can help Twitter users more easily grasp information from users they take interest in following and also facilitate many downstream applications, for example realtime friend recommendation.
- Triggerless Backdoor Attack for NLP Tasks with Clean Labels109
A new strategy to perform textual backdoor attack which does not require an external trigger and the poisoned samples are correctly labeled is proposed, which marks the first step towards developing triggerless attacking strategies in NLP.
- CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks106
A novel Conditional wATERmarking framework (CATER) is proposed for protecting the IP of text generation APIs and it is proved that it is infeasible for even the savviest attacker to reveal the used watermarks from a large pool of potential word pairs based on statistical inspection.
- 99
- 97
- Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints96
This work proposes a simple yet effective approach for incorporating side information in the form of distributional constraints over the generated responses that generates responses that are much less generic without sacrificing plausibility.
- TopicSpam: a Topic-Model-Based Approach for Spam Detection92
A generative LDA-based topic modeling approach for fake review detection that can aptly detect the subtle differences between deceptive reviews and truthful ones and achieves about 95% accuracy on review spam datasets, outperforming existing baselines by a large margin.
- Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving83
The lane detection system is targeted, which is an indispensable module for many autonomous driving tasks, e.g., navigation, lane switching, and the first physical backdoor attacks to such system are designed and realized.
- 81
- 80
- Defending against Backdoor Attacks in Natural Language Generation71
By giving a formal definition of backdoor attack and defense, this work finds that testing the backward probability of generating sources given targets yields effective defense performance against all different types of attacks, and is able to handle the one-to-many issue in many NLG tasks such as dialog generation.
- CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning68
CUDA-L1 is introduced, an automated reinforcement learning framework for CUDA optimization that employs a novel contrastive RL algorithm that can transform an initially poor-performing LLM into an effective CUDA optimizer through speedup-based reward signals alone, without human expertise or domain knowledge.
- Deep Reinforcement Learning for NLP59
A gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP problems, with a special focus on generation, dialogue, and information extraction.
- Fast Nearest Neighbor Machine Translation55
Fast kNN-MT is proposed, which constructs a significantly smaller datastore for the nearest neighbor search, and is only two times slower than the standard NMT model, enabling the practical use of knn-MT systems in real-world MT applications.
- ENDA: embracing network inconsistency for dynamic application offloading in mobile cloud computing55
This work proposes ENDA, a three-tier architecture that leverages user track prediction, realtime network performance and server loads to optimize offloading decisions and outperforms existing offloading techniques that do not consider user mobility and server workload balance management.
- Identifying Manipulated Offerings on Review Portals53
A semi-supervised manifold ranking algorithm is introduced for identifying offerings that contain fake reviews, and a novel evaluation procedure is introduced that ranks artificial instances of real offerings, where each artificial offering contains a known number of injected deceptive reviews.
- Reflections on Sentiment/Opinion Analysis52
This paper focuses on two basic sources of human attitude—the holder’s non-logical/emotional preferences and the fulfillment of the holder's goals and examples of how sentiment systems could provide richer and more realistic accounts of sentiment in text.
- 49
- 48
- 46
- Evolutionary Hierarchical Dirichlet Process for Timeline Summarization45
A novel model called Evolutionary Hierarchical Dirichlet Process (EHDP) is developed to capture the topic evolution pattern in timeline summarization and demonstrates the good performance of the system with regard to ROUGE scores.
- 40
- VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking39
VideoShield is a novel watermarking framework specifically designed for popular diffusion-based video generation models that effectively extracts watermarks and detects tamper without compromising video quality and is applicable to image generation models, enabling tamper detection in generated images as well.
- Implicit discourse relation recognition by selecting typical training examples34
This paper is the first time to apply a d ifferent typical/atypical perspective to select the most suitable discourse relation examples as training data and proves that the proposed new method outperforms the state -of-the-art methods.
- 33
- Sentiment Analysis through LLM Negotiations31
This paper introduces a multi-LLM negotiation framework for sentiment analysis that is able to take the complementary abilities of two LLMs, have them use rationale to persuade each other for correction, and consistently yields better performances than the ICL baseline across all benchmarks.
- 30
- Exploring hypergraph-based semi-supervised ranking for query-oriented summarization30
A hypergraph based semi-supervised sentence ranking algorithm is developed for query-oriented extractive summarization, where the influence of query is propagated to sentences through the structure of the constructed text hypergraph.
- A Novel Feature-based Bayesian Model for Query Focused Multi-document Summarization26
A novel supervised approach is proposed that can incorporate rich sentence features into Bayesian topic models in a principled way, thus taking advantages of both topic model and feature based supervised learning methods.
- ConRPG: Paraphrase Generation using Contexts as Regularizer25
A pipelined system which consists of paraphrase candidate generation based on contextual language models, candidate filtering using scoring functions, and paraphrase model training based on the selected candidates, which significantly outperforms existing paraphrase approaches in both supervised and unsupervised setups.
- 25
- Dependency Parsing as MRC-based Span-Span Prediction24
The proposed method addresses the fundamental problem that edges in a dependency tree should be constructed between subtrees and the MRC framework allows the method to retrieve missing spans in the span proposal stage, which leads to higher recall for eligible spans.
- 22
- A novel topic model for automatic term extraction22
This paper proposes to compute termhood based on semantic representation of words based on i-SWB, a novel topic model developed to map the domain corpus into a latent semantic space, which is composed of some general topics, a background topic and a documents-specific topic.
- Self Question-answering: Aspect-based Sentiment Analysis by Role Flipped Machine Reading Comprehension21
This paper investigates the ABSA task from the perspective of Machine Reading Comprehension by observing that the aspect and the opinion terms can serve as the query and answer in MRC in-terchangeably, and proposes a new paradigm named Role Flipped Machine Readingcomprehension (RF-MRC) to resolve.
- 20
- Deep Adversarial Learning for NLP19
This tutorial provides a gentle introduction to the foundation of deep adversarial learning, as well as some practical problem formulations and solutions in NLP.
- Smartphone-assisted energy efficient data communication for wearable devices19
This work proposes a Lyapunov based on-line approach designation mechanism that dynamically chooses an appropriate data communication approach based on data transmission queue, estimated network conditions and the device moving speed and demonstrates that this mechanism delivers very close performance to the mechanism that can foresee the future.
- Update Summarization Using a Multi-level Hierarchical Dirichlet Process Model19
This paper borrows the idea of evolutionary clustering and proposes a three-level HDP model named h-uHDP, which reveals the diversity and commonality between aspects discovered from two different epochs (i.e. epoch history and epoch update).
- 18
- 18
- Sentiment Analysis on the People's Daily18
A semi-supervised bootstrapping algorithm for analyzing China’s foreign relations from the People's Daily is proposed, different from existing algorithms in the literature, time information is considered in the algorithm through a hierarchical bayesian model to guide thebootstrapping approach.
- Are Human-generated Demonstrations Necessary for In-context Learning?17
Self-contemplation prompting strategy (SEC) is proposed, a paradigm free from human-crafted demonstrations that demonstrates that, for many tasks, contemporary LLMs possess a sufficient level of competence to exclusively depend on their own capacity for decision making, removing the need for external training data.
- 16
- Improving Adversarial Robustness of 3D Point Cloud Classification Models15
Two innovative methodologies to improve the adversarial robustness of 3D point cloud classification models are designed, including a novel point cloud architecture which can smooth and disrupt the adversarial perturbations and a novel data augmentation strategy to adaptively balance the model usability and robustness.
- 14
- Similarity-based Neighbor Selection for Graph LLMs14
Using SimCSE and advanced neighbor selection techniques, SNS effectively improves the quality of selected neighbors, thereby improving graph representation and alleviating issues like over-squashing and heterophily, and demonstrates superior generalization and scalability over traditional GNN methods.
- 14
- 14
- 12
- 12
- 12
- $k$NN-NER: Named Entity Recognition with Nearest Neighbor Search11
A nearest neighbor NER framework, which augments the distribution of entity labels by assigning nearest neighbors retrieved from the training set, which makes the model more capable of handling long-tail cases, along with better few-shot learning abilities.
- 11
- 11
- 11
- Exploring simultaneous keyword and key sentence extraction11
A two- level graph based ranking algorithm to generate summarization and extract keywords at the same time and uses Wikipedia to build a two-level concept-based graph, instead of traditional term-based graphs to express their homogenous relationship and heterogeneous relationship.
- PK-ICR: Persona-Knowledge Interactive Multi-Context Retrieval for Grounded Dialogue10
This work develops a novel grounding retrieval method that utilizes all contexts of dialogue simultaneously and introduces a novel null-positive rank test which measures ranking performance on semantically dissimilar samples (i.e. hard negatives) in relation to data augmentation.
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 7
- 7
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- MDFN: Enhancing Power Grid Image Quality Assessment via Multi-Dimension Distortion Feature4
A multi-dimension distortion feature network (MDFN) based on CNN and Transformer is proposed, which considers high-frequency and low-frequency features of images, along with noise and brightness features, to achieve more accurate quality assessment.
- 4
- 4
- 4
- One Shot Domain Adaptation for Person Re-Identification4
This work introduces a similarity-guided strategy to progressively assign pseudo labels to unlabeled instances with different confidence scores, which are in turn leveraged as weights to guide the optimization as training goes on and makes significant improvement in the domain adaptation tasks of re-ID.
- Cascaded CNN-resBiLSTM-CTC: An End-to-End Speech Recognition Acoustic Model4
This work proposes a novel end-to-end deep learning model architecture namely cascaded CNN-resBiLSTM-CTC, which adds residual blocks in BiL STM layers to extract sophisticated phoneme and semantic information together, and applies cascaded structure to pay more attention mining information of hard negative samples.
- 3
- 3
- 3
- 3
- 3
- 3
- Black-Box Extraction of Functional Structures from System Call Traces for Intrusion Detection3
This paper proposes a novel approach, which analyzes property of individual system call and its context at semantic level to discover function structures from system call traces efficiently without any static analysis of source code or runtime information.
- 3
- A localized differential privacy-based location preservation method using a hidden Markov model in vehicular networks2
A localized differential privacy location protection method based on the hidden Markov model (HMM) in vehicular networks, which addresses the problem of vehicle location privacy protection and provides strong privacy protection, high data availability, and efficient processing.
- 2
- 2
- 2
- 2
- Design and implementation of distributed asynchronous data aided computer information interaction system2
A flexible and universal asynchronous interaction architecture of distributed system is established based on Web service technology and system to system access that is suitable for the data interaction of distributed personal management system under the influence of novel corona virus pneumonia epidemic prevention and control.
- 2
- Agent Based Adaptive Cooperative Models and Mechanisms of Multiple Autonomous Cyber-Physical Systems2
- Fingerprinting Image-to-Image Generative Adversarial Networks1
A novel finger-printing scheme for the Intellectual Property (IP) protection of image-to-image GANs based on a trusted third party and proves that these methods can satisfy different security requirements necessary for IP protection.
- 1
- PK-ICR: Persona-Knowledge Interactive Context Retrieval for Grounded Dialogue1
A novel grounding retrieval method is developed that utilizes all contexts of dialogue simultaneously while also requiring limited training via zero-shot inference due to compatibility with neural Q & A retrieval models and the hard-negative behavior of combining Persona and Dialogue is analyzed.
- Emage: Non-Autoregressive Text-to-Image Generation1
This work explores non-autoregressive text-to-image models that efficiently generate hundreds of image tokens in parallel and runs 16 times to generate images of competitive quality with an order of magnitude lower inference latency.
- 1
- ShiftNAS: Towards Automatic Generation of Advanced Mulitplication-Less Neural Networks1
This work proposes ShiftNAS, the first framework tailoring Neural Architecture Search (NAS) to substantially reduce the accuracy gap between bit-shift neural networks and their real-valued counterparts, and sets a new state-of-the-art for bit- shift neural networks.
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- The CW-XMU System For CHiME-6 Challenge–
In this paper, Cloudwalk Technology and Xiamen Universitys joint effort for CHiME-6 Challenge to recog-nize highly-overlapped and very natural conversational speech in dinner party environment is presented and DNN-HMM hybrid system for track 1 rank A and end-to-end model is explored.
- –
- –
- –
- The Application of Computer and Internet in FLT and Its Problems–
Integrate the computer and internet technology with the superiority of traditional FLT, they are bound to facilitateFLT, and improve students' foreign language ability.
- –
- –
- Countermeasure Research and Reason of Performance Different for Men's Decathlon between Home and Abroad–
The result shows that single events and technical grade of decathlon develop unbalance, the performance between home and abroad has great different, and throw event is the key factor to influence the development of the authors' decathlon.
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.