研究方向：自然语言处理、多模态分析、认知计算

具体包括：情感分析、问答系统、文本生成、大模型轻量化等

1. 具备推免资格，计算机相关专业，具有良好的数学、英语、编程、逻辑能力；

2. 本科期间发表过人工智能、自然语言处理等领域论文优先；

3. 希望保研生大四可以来实验室客座或者远程毕设，打好基础，做好科研过渡；

想要更多了解小组情况，可以关注：iienlp.github.io

081203-计算机应用技术

自然语言处理，多模态分析

   

2022-10~现在, 中国科学院信息工程研究所, 研究员
2016-10~2022-10,中国科学院信息工程研究所, 副研究员
2014-07~2016-10,中国科学院信息工程研究所, 助理研究员

2022-07-01-2027-07-31,中国指挥与控制学会, 信息融合专委会委员
2022-01-01-今,NeurIPS审稿人,
2022-01-01-今,ICML审稿人,
2021-01-01-今,ACL 2021 审稿人,
2021-01-01-今,EMNLP 2021 审稿人,
2021-01-01-今,AAAI 2021审稿人,
2019-08-30-2024-08-31,CCF大数据专委通讯委员,
2018-01-01-今,IEEE-ACM Transactions on Audio Speech and Language Processing审稿人,
2016-01-01-今,中文信息学报审稿人,
2016-01-01-今,计算机学报审稿人,

信息检索导论
文献阅读
深度学习与自然语言处理

   

（1） 军事科学技术进步奖, 一等奖, 部委级, 2022
（2） 全国第二届军事智能-机器阅读挑战赛, 一等奖, 国家级, 2019
（3） F5000优秀论文, 部委级, 2019
（4） 全国第一届军事智能-机器阅读挑战赛, 一等奖, 国家级, 2018

1. A Pedestrian is Worth One Prompt: Towards Language Guidance Person Re-Identification. CVPR, 2024

2. Object Attribute Matters in Visual Question Answering. AAAI, 2024

3. Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation. EMNLP, 2023

4. Compressing and Debiasing Vision-Language Pre-Trained Models for Visual Question Answering. EMNLP, 2023

5. An Empirical Study of Instruction-tuning Large Language Models in Chinese.  findings of EMNLP, 2023

6. Chain-of-Thought Reasoning in Tabular Language Models. findings of EMNLP, 2023

7. IM-TQA: A Chinese Table Question Answering Dataset with Implicit and Multi-type Table Structures. ACL, 2023

8. Combo of Thinking and Observing for Outside-Knowledge VQA. ACL, 2023

9. A Gradient Control Method for Backdoor Attacks on Parameter-Efficient Tuning. ACL, 2023

10. Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension. Findings of  ACL, 2023

11. Maximum Entropy Loss, the Silver Bullet Targeting Backdoor Attacks in Pre-trained Language Models. Findings of  ACL, 2023

12. Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking. ACL, 2023

13. DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation. ACL, 2023

14. Retrieve-and-Sample: Document-level Event Argument Extraction via Hybrid Retrieval Augmentation. ACL, 2023

15. Explainable Hyperbolic Temporal Point Process for User-Item Interaction Sequence Generation. TOIS, 2023

16. Multi-Aspect Heterogeneous Graph Augmentation. WWW, 2023

17. Towards Polymorphic Adversarial Examples Generation for Short Text. ICASSP, 2023

18. SERI: SkEtching-Reasoning-Integrating Progressive Workflow for Empathetic Response Generation. ICASSP, 2023

19. Explainable Hyperbolic Temporal Point Process for User-Item Interaction Sequence Generation. ACM Transactions on Information Systems, 2022

20. A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models. NeurIPS, 2022 
21. Detach and Attach: Stylized Image Captioning without Paired Stylized Dataset. ACM MM, 2022
22. Neutral Utterances are Also Causes: Enhancing Conversational Causal Emotion Entailment with Social Commonsense Knowledge. IJCAI, 2022
23. Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization. ACL, 2022
24. COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models. EMNLP, 2022
25. Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA. findings of EMNLP, 2022
26. Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection. findings of EMNLP, 2022
27. Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning. findings of EMNLP, 2022
28. Target Really Matters: Target-aware Contrastive Learning and Consistency Regularization for Few-shot Stance Detection. COLING, 2022

29. TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation. COLING, 2022

30. Slot Dependency Modeling for Zero-Shot Cross-Domain Dialogue State Tracking. COLING, 2022

31. CLIO: Role-interactive Multi-event Head Attention Network for Document-level Event Extraction. COLING, 2022

32. Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training. NAACL, 2022
33. Cross-Target Stance Detection via Refined Meta-Learning. ICASSP, 2022
34. Connecting Targets via Latent Topics and Contrastive Learning: A Unified Framework for Robust Zero-shot and Few-shot Stance Detection. ICASSP, 2022
35. Addressing Extraction and Generation Separately:  Keyphrase Prediction with Pre-trained Language Models. IEEE Transactions on Audio, Speech and Language Processing, 2021
36. Sarcasm Detection with Commonsense Knowledge. IEEE Transactions on Audio, Speech and Language Processing, 2021
37. Past, Present, and Future: Conversational Emotion Recognition through Structural Modeling of Psychological Knowledge. Findings of EMNLP, 2021
38. Check It Again: Progressive Visual Question Answering via Visual Entailment. ACL, 2021
39. Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation. ACL, 2021
40. Enhanching Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph. Findings of  ACL, 2021
41. ROSITA: Refined BERT Compression with Integrated Technique. AAAI, 2021
42. Learning Class-Transductive Intent Representations for Zero-shot IntentDetection. IJCAI, 2021
43. MACROBERT: Maximizing Certified Region of BERT to Adversarial Word Substitutions. DASFAA, 2021
44. Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection. Findings of EMNLP, 2020
45. Joint Character-Level Word Embedding and Adversarial Stability Training to Defend Adversarial Text. AAAI, 2020
46. Modeling the Incongruity between Sentence Snippets for Sarcasm Detection. ECAI, 2020
47. Generating Paraphrase with Topic as Prior Knowledge. CIKM, 2019
48. Ranking and Sampling in Open-Domain Question Answering. EMNLP, 2019
49. Learning Sentiment-Specific Word Embedding via Global Sentiment Representation. AAAI, 2018
50. Deep Uniqueness-aware Hashing for Fine-grained Multi-label Image Retrieval. ICASSP, 2018
51. Deep Supervised Hashing for Multi-Label and Large-Scale Image Retrieval. ICMR, 2017
52. An Unsupervised Cross-Lingual Topic Model Framework for Sentiment Classification, IEEE/ACM Transactions on Audio, Speech and Language Processing, 2016
53. A Word Vector and Matrix Factorization Based Method for Opinion Lexicon Extraction. WWW, 2015
54. A Cross-Lingual Joint  Aspect/Sentiment Model for Sentiment Analysis. CIKM, 2014
55. Towards jointly extracting aspects and aspect-specific sentiment knowledge. CIKM, 2012
56. Find me opinion sources in blogosphere: a unified framework for opinionated blog feed retrieval. WSDM, 2012
57. Effective and efficient?bilingual sentiment lexicon extraction using collocation alignment. CIKM, 2012
58. Language-independent sentiment classification using three common words. CIKM, 2011
59. 智能回复系统研究综述. 信息安全学报，2020
60. 文本情绪分析综述. 计算机研究与发展，2018
61. 一种面向大规模社会信息网络的多层社区发现算法. 计算机学报，2016

（1） 文本情感分析, Text Sentiment Analysis, 清华大学出版社, 2019-12, 第 1 作者
（2） 情感分析进阶, Advanced Sentiment Analysis, 机械工业出版社, 2023-03, 第 1 作者

（ 1 ） 短文本情感分析关键技术研究, 负责人, 国家任务, 2016-01--2018-12
（ 2 ） 态势感知技术研究, 负责人, 国家任务, 2019-02--2022-01
（ 3 ） 情绪感知与知识增强的文本生成技术研究, 负责人, 国家任务, 2020-01--2023-12
（ 4 ） 网络信息平台（一期）, 参与, 国家任务, 2016-05--2017-11
（ 5 ） 网络信息平台（二期）, 参与, 国家任务, 2019-09--2021-09
（ 6 ） 识别与消解技术（一期）, 负责人, 国家任务, 2018-10--2019-09
（ 7 ） 识别与研判技术（二期）, 负责人, 国家任务, 2019-10--2020-09
（ 8 ） 大模型轻量化, 负责人, 国家任务, 2023-06--2025-06
（ 9 ） 多模态情绪分析, 负责人, 国家任务, 2023-11--2025-11
（ 10 ） 大模型推理技术, 负责人, 境内委托项目, 2023-05--2024-05