杨敏,博士生导师,中国科学院青年创新促进会成员, 深圳市海外高层次人才。入选第九届中国科协青年人才托举工程,连续三年入选全球前2%顶尖科学家, 入选百度2022年度AI华人青年学者榜单等。长期从事人工智能、自然语言处理相关研究,发表高水平学术论文200余篇,谷歌学术引用 7600余次,H-index 47。获得2022年度深圳市人工智能自然科学奖、2019年度CCF-腾讯犀牛鸟基金优秀专利奖、2023年度阿里巴巴优秀学术合作项目奖等。多次担任ACL、NeurIPS、EMNLP、COLING、NAACL等自然语言处理顶级会议的(高级)领域主席。
l学习经历:
Ø2012年-2017年,香港大学,计算机科学,博士
Ø2008年-2012年,四川大学,软件工程,学士
l工作经历:
Ø2022年-至今,中国科学院深圳先进技术研究院/数字所,数据挖掘实验室主任
Ø2017年-至今,中国科学院深圳先进技术研究院/数字所,历任助理研究员、副研究员
l学术成果
入选第九届中国科协青年人才托举工程,连续三年入选全球前2%顶尖科学家, 入选百度2022年度AI华人青年学者榜单等。多次担任ACL、NeurIPS、EMNLP、COLING、NAACL等自然语言处理顶级会议的(高级)领域主席。
l所获荣誉
获得2024年重庆市自然科学二等奖、2022年度深圳市人工智能自然科学奖、中国人工智能学会2018年度最佳青年科技成果奖、2019年度CCF-腾讯犀牛鸟基金优秀专利奖、2023及2024年度阿里巴巴优秀学术合作项目奖、第五届全国青年人工智能创新创业大赛一等奖等。
l科研成果
代表性论文:
1.Hierarchical Human-like Deep Neural Networks for Abstractive Text Summarization,IEEE Transactions on Neural Networks and Learning Systems,2021,排名:1(中科院一区,IF=10.4)
2.Multitask Learning and Reinforcement Learning for Personalized Dialog Generation: An Empirical Study, IEEE Transactions on Neural Networks and Learning Systems,2021,排名:1(中科院一区,IF=10.4)
3.An Effective Hybrid Learning Model for Real-time Event Summarization,IEEE Transactions on Neural Networks and Learning Systems,2021,排名:1(中科院一区,IF=10.4)
4.Modeling Relation Paths for Knowledge Graph Completion,IEEE Transactions on Knowledge and Data Engineering, 2021,排名:5(通讯作者,中科院二区,IF=8.9)
5.Exploring Privileged Features for Relation Extraction with Contrastive Student-Teacher Learning,IEEE Transactions on Knowledge and Data Engineering, 2022,排名:2(通讯作者,中科院二区,IF=8.9)
6.A Survey of Natural Language Generation. ACM Computing Surveys (CSUR), 2022,排名:7(通讯作者,中科院一区,IF=16.6)
7.Few-shot Aspect Category Sentiment Analysis via Meta-learning,ACM Transactions on Information Systems (TOIS), 2023,排名:6(通讯作者,CCF-A)
8.Improving Semi-Supervised Text Classification with Dual Meta-Learning. ACM Transactions on Information Systems (TOIS),2024,排名:3(通讯作者,CCF-A)
9.Unifying Structured Data as Graph for Data-to-Text Pre-Training. Transactions of the Association for Computational Linguistics (TACL), 2024,排名:4(通讯作者,中科院一区,IF=10.6)
10.Few-Shot Relation Extraction with Automatically Generated Prompts. IEEE Transactions on Neural Networks and Learning Systems, 2024,排名:4(通讯作者,中科院一区,IF=10.4)
11.Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation. The International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2022,本人排名: 3(通讯作者,CCF-A)
12.Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing. The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022,本人排名: 5(通讯作者,CCF-A)
13.Effective Open Intent Classification with K-Center Contrastive Learning and Adjustable Decision Boundary. The AAAI Conference on Artificial Intelligence (AAAI), 2023,本人排名:4(通讯作者,CCF-A)
14.Balanced Meta Learning and Diverse Sampling for Lifelong Task-oriented Dialogue Systems. The AAAI Conference on Artificial Intelligence (AAAI), 2023,本人排名:2(通讯作者,CCF-A)
15.Speech-Text Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment. The Annual Meeting of the Association for Computational Linguistics (ACL), 2023,本人排名: 4(通讯作者,CCF-A)
16.PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts. The Annual Meeting of the Association for Computational Linguistics (ACL), 2023,本人排名: 4(通讯作者,CCF-A)
17.Large Language Models are Versatile Decomposers: Decomposing Evidence and Questions for Table-based Reasoning. The International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2023,本人排名: 3(通讯作者,CCF-A)
18.DiffusionTrack: Diffusion Model For Multi-Object Tracking. Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024,本人排名: 6(通讯作者,CCF-A)
19.Counterfactual-Enhanced Information Bottleneck for Aspect-Based Sentiment Analysis. Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024,本人排名: 2(通讯作者,CCF-A)
20.Iterative Forward Tuning Boosts In-Context Learning in Language Models.The Annual Meeting of the Association for Computational Linguistics (ACL), 2024,本人排名:3(通讯作者,CCF-A)