基本信息
林政  女  博导  中国科学院信息工程研究所
电子邮件: linzheng@iie.ac.cn
通信地址: 北京市海淀区树村路19号中科院信工所2号楼
邮政编码: 100195

研究领域

研究方向:自然语言处理、深度学习

具体包括:情感/情绪分析、机器阅读/问答系统、预训练模型压缩、文本对抗等

招生信息

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

招生专业
081203-计算机应用技术
招生方向
自然语言处理,深度学习

教育背景

2007-09--2014-07   中国科学院计算技术研究所   博士
2003-09--2007-07   天津师范大学   学士

工作经历

   
工作简历
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
社会兼职
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,

教授课程

信息检索导论
文献阅读
深度学习与自然语言处理

专利与奖励

   
奖励信息
(1) 全国第二届军事智能-机器阅读挑战赛, 一等奖, 国家级, 2019
(2) F5000优秀论文, 部委级, 2019
(3) 全国第一届军事智能-机器阅读挑战赛, 一等奖, 国家级, 2018

出版信息

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

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

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

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

发表著作
(1) 文本情感分析, Text Sentiment Analysis, 清华大学出版社, 2019-12, 第 1 作者

科研活动

科研项目
( 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

组内毕业生情况

博士生:

1. 付鹏   2018年毕业  中科院信工所(留所)

2. 李然   2020年毕业  广州大学

3. 袁凤程 2020年毕业 美团


硕士生:

1. 冯多  2016年毕业  阿里巴巴

2. 沈津生 2018年毕业  阿里巴巴

3. 岳世峰  2019年毕业  快手

4. 许彦夫  2020年毕业  腾讯微信

5. 耿悦  2020年毕业  公务员

6. 吴行  2020年毕业  百度