- Information Retrieval, Text Classification and QA.- Enhancing Free-Form Table Question Answering Models by Distilling Relevant-Cell-Based Rationales.- Enhangcing Sequence Representation for Personalized Search.- Joint Similarity Guidance Hash Coding Based on Adaptive Weight Mixing Strategy For Cross-Modal Retrieval.- Text Generation, Dialogue and Summarization.- Generate-then-Revise: An Effective Synthetic Training Data Generation framework for Event Detection.- Machine Translation and Multilingual Information Processing.- E³: Optimizing Language Model Training for Translation via Enhancing Efficiency and Effectiveness.

- Multi-features Enhanced Multi-task Learning for Vietnamese Treebank Conversion.- SimCLNMT: A Simple Contrastive Learning Method for Enhancing Neural Machine Translation Quality.- Translate-and-Revise: Boosting Large Language Models for Constrained Translation.- Knowledge Graph and Information Extraction.- A Multi-Task Biomedical Named Entity Recognition Method Based on Data Augmentation.- Biomedical Event Causal Relation Extraction by Reasoning Optimal Entity Relation Path.- Joint Entity and Relation Extraction Based on Bidirectional Update and Long-Term Memory Gate Mechanism.- MFE-NER:Multi-feature Fusion Embedding for Chinese Named Entity Recognition.

- UDAA: An Unsupervised Domain Adaptation Adversarial Learning Framework for Zero-Resource Cross-Domain Named Entity Recognition.- Social Computing and Sentiment Analysis.- Triple-view Event Hierarchy Model for Biomedical Event Representation.- NLP Applications.- DialectMoE: An End-to-End Multi-Dialect Speech Recognition Model with Mixture-of-Experts.- Distinguishing Neural Speech Synthesis Models Through Fingerprints in Speech Waveforms.- Knowledge Graph-Enhanced Recommendation with Box Embeddings.- Readability-guided Idiom-aware Sentence Simplification(RISS) for Chinese.

- Fundamental Theory and Method of Language Computing and Cognition.- A Tone-based Hierarchical Structure of Chinese Prosody.- Linguistic Guidance for Sequence-to-Sequence AMR Parsing.- Language Resource and Evaluation.- Automatic Construction of the English Sentence Pattern Structure Treebank for Chinese ESL learners.- Cost-efficient Crowdsourcing for Span-based Sequence Labeling:Worker Selection and Data Augmentation.- DLUE: Benchmarking Document Language Understanding.- Do Large Language Models Understand Conversational Implicature- A case study with a Chinese sitcom.

- EmoFake: An Initial Dataset for Emotion Fake Audio Detection.- Going Beyond Passages:Readability Assessment for Book-level Long Texts.- Mitigating the Bias of Large Language Model Evaluation.- PPDAC: A Plug-and -Play Data Augmentation Component for Few-shot Extractive Question Answering.- Sentence-Space Metrics (SSM) for the Evaluation of Sentence Comprehension.- Large Language Models.- AuditWen: An Open-Source Large Language Model for Audit.- Chinese Grammatical Error Correction via Large Language Model Guided Optimization Training.

- Pattern Shifting or Knowledge Losing? A Forgetting Perspective for Understanding the Effect of Instruction Fine-Tuning.- Prior Constrains-based Reward Model Training for Aligning Large Language Models.- Prompt Engineering 101 Prompt Engineering Guidelines from a Linguistic Perspective.