Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Sheng LiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works184 from public data
- CodeBERT: A Pre-Trained Model for Programming and Natural Languages4,421
This work develops CodeBERT with Transformer-based neural architecture, and trains it with a hybrid objective function that incorporates the pre-training task of replaced token detection, which is to detect plausible alternatives sampled from generators.
- Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification1,229
Three neural networks are developed to effectively incorporate the supervision from sentiment polarity of text (e.g. sentences or tweets) in their loss functions and the performance of SSWE is improved by concatenating SSWE with existing feature set.
- Aspect Level Sentiment Classification with Deep Memory Network1,041
A deep memory network for aspect level sentiment classification that explicitly captures the importance of each context word when inferring the sentiment polarity of an aspect, and is also fast.
- Effective LSTMs for Target-Dependent Sentiment Classification1,010
Two target dependent long short-term memory models, where target information is automatically taken into account, are developed, which achieve state-of-the-art performances without using syntactic parser or external sentiment lexicons.
- Learning Semantic Representations of Users and Products for Document Level Sentiment Classification365
By combining evidence at user-, product and documentlevel in a unified neural framework, the proposed model achieves state-of-the-art performances on IMDB and Yelp datasets1.
- 335
- Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting278
A recall and learn mechanism, which adopts the idea of multi-task learning and jointly learns pretraining tasks and downstream tasks, and an Objective Shifting mechanism to focus the learning on downstream tasks gradually.
- Coooolll: A Deep Learning System for Twitter Sentiment Classification251
A neural network with hybrid loss function 1 is developed to learn SSWE, which encodes the sentiment information of tweets in the continuous representation of words, which can be easily re-implemented with the publicly available sentiment-specific word embedding.
- Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network210
A Label-enhanced Task-Adaptive Projection Network (L-TapNet) based on the state-of-the-art few-shot classification model – TapNet is proposed, by leveraging label name semantics in representing labels.
- Deep learning for sentiment analysis: successful approaches and future challenges207
An overview of the successful deep learning approaches for sentiment analysis tasks is provided, lay out the remaining challenges and provide some suggestions to address these challenges.
- N-LTP: An Open-source Neural Language Technology Platform for Chinese172
N-LTP, an open-source neural language technology platform supporting six fundamental Chinese NLP tasks: lexical analysis (Chinese word segmentation, part-of-speech tagging, and named entity recognition), syntactic parsing (dependency parsing), and semantic parsing (semantic dependency parsing and semantic role labeling).
- A Co-Interactive Transformer for Joint Slot Filling and Intent Detection156
This paper proposes a co-interactive module to consider the cross-impact by building a bidirectional connection between the two related tasks, where slot and intent can be able to attend on the corresponding mutual information.
- 147
- CharBERT: Character-aware Pre-trained Language Model131
This paper proposes a character-aware pre-trained language model named CharBERT improving on the previous methods (such as BERT, RoBERTa) and proposes a new pre-training task named NLM (Noisy LM) for unsupervised character representation learning.
- 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.
- Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure125
The Molweni dataset is presented, a machine reading comprehension (MRC) dataset with discourse structure built over multiparty dialog with large-scale annotations in a modified Segmented Discourse Representation Theory (SDRT; Asher et al., 2016) style.
- A Neural Multi-Task Learning Framework to Jointly Model Medical Named Entity Recognition and Normalization123
A novel deep neural multi-task learning framework with explicit feedback strategies to jointly model recognition and normalization that performs significantly better than state-of-the-art approaches on two publicly available medical literature datasets.
- Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization114
DialoGPT, a pre-trained model for conversational response generation, can be developed as an unsupervised dialogue annotator, which takes advantage of dialogue background knowledge encoded in DialoG PT.
- Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation101
- Event causality extraction based on connectives analysis90
The advantage of this model lies in its ability to cope with partial interactions among features so as to avoid over-fitting problem on Hidden Naive Bayes model, especially the interaction between the connective category and the syntactic structure of sentences.
- 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.
- An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming86
An expressive entity-mention model that performs coreference resolution at an entity level that adopts the Inductive Logic Programming (ILP) algorithm, which provides a relational way to organize different knowledge of entities and mentions.
- Semantic Parsing with Syntax- and Table-Aware SQL Generation83
The quality of the generated SQL query is significantly improved through learning to replicate content from column names, cells or SQL keywords; and improving the generation of WHERE clause by leveraging the column-cell relation.
- 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.
- Hierarchical Attention Flow for Multiple-Choice Reading Comprehension78
This paper presents the hierarchical attention flow to adequately leverage candidate options to model the interactions among passages, questions and candidate options and explicitly model the option correlations with attention mechanism to obtain better option representations.
- Hashtag recommendation with topical attention-based LSTM78
Experimental results show that the model significantly outperforms various competitive baseline methods and the incorporation of topical attention mechanism gives more than 7.4% improvement in F1 score compared with standard LSTM method.
- From static to dynamic word representations: a survey76
This survey provides a comprehensive typology of word representation models from a novel perspective that the development from static to dynamic embeddings can effectively address the polysemy problem.
- A Neural Transition-Based Approach for Semantic Dependency Graph Parsing69
A neural transition-based parser, using a variant of list-based arc-eager transition algorithm for dependency graph parsing, and two non-trivial improvements are proposed for representing the key components of the transition system, to better capture the semantics of segments and internal sub-graph structures.
- Few-shot Learning for Multi-label Intent Detection65
The proposed model significantly outperforms strong baselines in both one-shot and five-shot settings and introduces label name embedding as anchor points in representation space, which refines representations of different classes to be well-separated from each other.
- Event Representation Learning Enhanced with External Commonsense Knowledge65
Experiments on three event-related tasks show that the proposed model obtains much better event embeddings for the tasks, achieving 78% improvements on hard similarity task, yielding more precise inferences on subsequent events under given contexts, and better accuracies in predicting the volatilities of the stock market.
- Improving Low Resource Named Entity Recognition using Cross-lingual Knowledge Transfer65
A lexicon extension strategy is designed to address out-of lexicon problem by automatically learning semantic projections and regard word-level entity type distribution features as an external language-independent knowledge and incorporate them into the neural architecture.
- 58
- Multi-Task Self-Supervised Learning for Disfluency Detection57
This work investigates methods for combining multiple self-supervised tasks-i.e., supervised tasks where data can be collected without manual labeling to tackle the training data bottleneck in disfluency detection.
- A Graph-based Method for Entity Linking55
This paper formalizes the task of finding a knowledge base entry that a given named entity mention refers to, namely entity linking, by identifying the most “important” node among the graph nodes representing the candidate entries by introducing three degree-based measures of graph connectivity.
- Context-Sensitive Generation of Open-Domain Conversational Responses53
Experimental results on two public datasets show that the proposed static attention based approach outperforms all the baselines on automatic and human evaluation.
- Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Trustworthy Response Generation in Chinese48
Experimental results show that the LLMs which are knowledge-tuned with cMedKnowQA can exhibit higher levels of accuracy in response generation compared with vanilla instruction-tuning and offer a new trustworthy way for the domain adaptation of LLMs.
- Cross-Lingual Machine Reading Comprehension48
A novel model called Dual BERT is proposed, which takes advantage of the large-scale training data provided by rich-resource language and learn the semantic relations between the passage and question in bilingual context, and then utilize the learned knowledge to improve reading comprehension performance of low- resource language.
- Learning to Ask Unanswerable Questions for Machine Reading Comprehension46
A pair-to-sequence model for unanswerable question generation, which effectively captures the interactions between the question and the paragraph, and a way to construct training data for question generation models by leveraging the existing reading comprehension dataset is presented.
- Collocation Polarity Disambiguation Using Web-based Pseudo Contexts45
This paper proposes an unsupervised three-component framework to expand some pseudo contexts from web, to help disambiguate a collocation's polarity.
- Chinese Grammatical Error Diagnosis with Long Short-Term Memory Networks42
This paper introduces the Chinese Grammatical Error Diagnosis (CGED) system in the NLP-TEA-3 shared task for CGED, and treats the CGED task as a sequence labeling task and describes three models, including a CRF-based model, an LSTM- based model and an ensemble model using stacking.
- 40
- An AMR Aligner Tuned by Transition-based Parser39
A new rich resource enhanced AMR aligner which produces multiple alignments and a new transition system for AMR parsing along with its oracle parser and a transition-based AMR parser that parses a sentence into its AMR graph directly are proposed.
- 39
- Aligning Semantic in Brain and Language: A Curriculum Contrastive Method for Electroencephalography-to-Text Generation37
A Curriculum Semantic-aware Contrastive Learning strategy (C- SCL), which effectively recalibrates the subject-dependent EEG representation to the semantic- dependent EEG representation, thereby reducing the discrepancy.
- 37
- Contradiction Detection with Contradiction-Specific Word Embedding35
A tailored neural network to learn contradiction-specific word embedding (CWE), which can separate antonyms in the opposite ends of a spectrum and performs comparably with the top-performing system in accuracy of three-category classification.
- Integrating Intra- and Inter-document Evidences for Improving Sentence Sentiment Classification35
A graph-based propagation approach is presented to incorporate inside and outside sentence features to improve the sentence sentiment classification performance, and the experimental results on camera domain show that the proposed approach performs better than the approaches without usingoutside sentence features, and outperforms other representational previous approaches.
- 33
- Comment Target Extraction and Sentiment Classification33
An intensive study of the two stages of sentiment analysis: the comment target extraction and the corresponding sentiment classification, which combines PMI based on web mining and NN filtering algorithm to decide the targets.
- A novel approach to update summarization using evolutionary manifold-ranking and spectral clustering32
A novel content selection framework based on evolutionary manifold-ranking and normalized spectral clustering that aims to capture the temporal characteristics and relay propagation of information in dynamic data stream and user need is proposed.
- 31
- 30
- 29
- Learning Sentence Representation for Emotion Classification on Microblogs27
Experimental results in the supervised learning framework show that using the pseudo-labeled data, the representation learned by Deep Belief Network outperforms the Principal Components Analysis based and Latent Dirichlet Allocation based representations.
- A survey of discourse parsing26
This survey introduces several different kinds of discourse parsing tasks, mainly including RST-style discourse parsing, PDTB-style discusses, and discourse parsing for multiparty dialogue, and discusses the future trends of the task.
- Transforming Wikipedia Into Augmented Data for Query-Focused Summarization26
This paper uses Wikipedia to automatically collect a large query-focused summarization dataset (named WikiRef) of more than 280,000 examples, which can serve as a means of data augmentation and develops a BERT-based query- focused summarization model (Q-BERT) to extract sentences from the documents as summaries.
- 26
- Personalized Microtopic Recommendation on Microblogs25
This article proposes a joint probabilistic latent factor model to integrate rich information into a matrix factorization-based solution to microtopic recommendation and shows that this model significantly outperforms a few competitive baseline methods, especially in the circumstance where users have few adoption behaviors.
- Exploiting Multiple Sources for Open-Domain Hypernym Discovery24
This paper proposes a simple yet effective distant supervision framework for Chinese open-domain hypernym discovery, and presents a heuristic strategy to build a large-scale noisy training data for the model without human annotation.
- Injecting Word Information with Multi-Level Word Adapter for Chinese Spoken Language Understanding22
Experimental results on two Chinese SLU datasets show that the proposed multi-level word adapter can capture useful word information and achieve state-of-the-art performance.
- Event type recognition based on trigger expansion22
This paper describes a method based on automatic expansion of the event triggers for event type recognition that improves the unbalanced data problem in training models and the data sparseness problem with a small corpus.
- Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching21
This work introduces SafePatching, a novel framework for comprehensive PSA, where two distinct safety patches are developed on the harmful data to enhance safety and mitigate over-safety concerns, and then seamlessly integrated into the target LLM backbone without compromising its utility.
- 21
- 21
- 20
- 20
- 19
- Encoding World Knowledge in the Evaluation of Local Coherence19
This paper introduces semantic relatedness as an enrichment to the original graph-based model of Guinaudeau and Strube (2013) and incorporates semantic relatednesses as additional features into the popular entity-based models of Barzilay and Lapata (2008).
- 18
- 18
- 17
- 17
- 15
- Multi-domain Spoken Language Understanding Using Domain- and Task-aware Parameterization15
This article proposes to improve the parameterization of this method by using domain-specific and task-specific model parameters for fine-grained knowledge representation and transfer and shows its transferability when adapting to a new domain with little data, outperforming the prior best model.
- Heterogeneous graph knowledge enhanced stock market prediction15
A novel heterogeneous neural network is presented to aggregate multi-grained information within financial text, which can be useful for context knowledge supplement and predictive information selection, and then improve the performance of stock market prediction.
- 14
- 14
- 14
- 14
- 13
- 13
- 13
- 12
- 12
- 12
- 12
- Deep Contextualized Word Embeddings for Universal Dependency Parsing12
Based on ELMo’s advantage on OOV, experiments that simulate low-resource settings are conducted and the results show that deep contextualized word embeddings are effective for data-insufficient tasks where the OOV problem is severe.
- ANEW+: Automatic Expansion and Validation of Affective Norms of Words Lexicons in Multiple Languages12
- Sentence Compression for Target-Polarity Word Collocation Extraction12
This work applies a discriminative conditional random field model, with some special sentimentrelated features, in order to automatically compress sentiment sentences.
- 12
- HIT-SCIR at SemEval-2020 Task 5: Training Pre-trained Language Model with Pseudo-labeling Data for Counterfactuals Detection11
This paper explores multiple pre-trained models to learn basic features and then fine-tune models with counterfactual data and pseudo-labeling data, which helps in detecting causation in texts.
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- 8
- 8
- Intra-document Coreference Resolution: The state of the art.8
It is pointed out that the current key problems and research trends are global optimization, the use of deep linguistical and background knowledge, and the combination of linguistical models and statistical models.
- Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning7
This work introduces a novel secure-tuning strategy called SWAT, which can be seamlessly integrated with pre-training and post-training methods, leading to greater improvements in security risks and task performance.
- Towards Stable Natural Language Understanding via Information Entropy Guided Debiasing7
A debiasing framework IEGDB is proposed that comprehensively detects the dataset biases to induce a set of biased features, and then purifies the biased features with the guidance of information entropy and can consistently improve the stability of performance on OOD datasets for aSet of widely adopted NLU models.
- 7
- 7
- 7
- Multi-level cross-lingual attentive neural architecture for low resource name tagging7
This paper combines multi-level cross-lingual knowledge as attention into a neural architecture, which guides low resource name tagging to achieve a better performance and is able to yield improvements in name tagging over all previous baselines.
- Product Aspect Clustering by Incorporating Background Knowledge for Opinion Mining7
Experimental results obtained demonstrate that the proposed product aspect clustering method based on two types of backgroundknowledge performs better than the baseline approach without the use of background knowledge, and indicate that expanding the available background knowledge using the Web is feasible.
- Building Chinese Event Type Paradigm Based on Trigger Clustering7
A novel approach of building an event type para- digm by clustering event triggers based on the trigger clusters, which can be built automatically and can be easily adapted to new domains.
- 7
- 7
- 6
- 6
- Personalized Microtopic Recommendation with Rich Information6
A novel hierarchical Bayesian model integrating user adoption behaviors, user item content information, and rich contextual information into the same principled model is proposed and Experimental results show that the model significantly outperforms a few baseline methods.
- Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation5
An unsupervised neural model with interactive attention mechanism is presented, used for learning the semantic relationship between records and reference texts to achieve better content transfer and better style preservation.
- 5
- 5
- 5
- Constructing Semantic Hierarchies via Fusion Learning Architecture5
A fusion learning architecture based on word embeddings for constructing semantic hierarchies, composed of discriminative generative fusion architecture and a very simple lexical structure rule for assisting, gets an F1-score of 74.20% with 91.60% precision-value, outperforming the state-of-the-art methods on a manually labeled test dataset.
- 5
- 5
- 5
- 5
- 4
- Interactive Gated Decoder for Machine Reading Comprehension4
An Interactive Gated Decoder (IG Decoder), which focuses on modeling the interactions between the answer span prediction and no-answer prediction with a gating mechanism, and a simple but effective approach for automatically generating pseudo training data, which aims to enrich the training data of the unanswerable questions.
- 4
- 4
- 4
- 3
- Improving Web Search Ranking by Incorporating Structured Annotation of Queries3
A method to improve web search ranking by detecting Structured Annotation of queries based on top search results, which involves splitting the original query into different units associated with semantic attributes in the corresponding domain.
- 3
- 2
- Prompt-based Context- and Domain-aware Pretraining for Vision and Language Navigation2
A novel Prompt-bAsed coNtext- and inDoor-Aware (PANDA) pretraining framework to address problems of VLN adaptation and experimental results on both R2R and REVERIE show the superiority of PANDA compared to existing state-of-the-art methods.
- 2
- 2
- 2
- 2
- 2
- Encoding Dependency Representation with Convolutional Neural Network for Target-Polarity Word Collocation Extraction2
A dependency representation is introduced to explore the most useful semantic features behind the syntactic rules and a framework based on a convolutional neural network (CNN) is adopted to extract the T-P collocations.
- Syntactic Processing Using Global Discriminative Learning and Beam-Search Decoding2
This tutorial discusses a framework for incremental left-to-right structured predication, which makes use of global discriminative learning and beam-search decoding, and gives an introduction to the algorithms and efficient implementations.
- 2
- 2
- 2
- 2
- Information Retrieval Technology : 4th Asia Information Retrieval Symposium, AIRS 2008: Harbin, China, January 15-18, 2008: Revised Selected Papers2
Improving Expertise Recommender Systems by Odds Ratio and Improving Spamdexing Detection Via a Two-Stage Classification Strategy are explored.
- 2
- 2
- 2
- 1
- Necessary and sufficient knowledge enhanced collaborative logical reasoning in LLMs1
This work contributes to remedy the inherent limitations of the logical reasoning paradigms in LLMs and lays the foundation for modeling human cognitive thinking.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.