Wei Shi is currently a staff AI researcher at Meituan M17. Prior to that, he received his Ph.D. Magna Cum Laude in December 2020 from Saarland University in Germany, where he worked on Natural Language Processing under the supervision of Prof. Dr. Vera Demberg at the Department of Language Science and Technology and Collaborative Research Center SFB-1102.
After graduation, he joined DAMO Academy, Alibaba Group as a Senior Algorithm Engineer in 2021, and later MiniMax Inc. in 2022, focusing on Large Language Models and Multimodal AI.
His research interests include Large Language Models, Multimodal AI, Discourse Relation Parsing, Sentiment Analysis, Text Generation, and Natural Language Understanding.
Education
-
Saarland UniversityPh.D. in Computational Linguistics
Advisor: Prof. Dr. Vera Demberg2016 - 2020 -
Chinese Academy of SciencesInstitute of AutomationM.Sc. in Computer Science2013 - 2016
-
Wuhan UniversityB.Eng. in Automation2008 - 2012
Experience
-
Meituan M17Staff AI ResearcherFeb. 2024 - present
-
MiniMax Inc.LLM Algorithm EngineerJun. 2022 - Jan. 2024
-
DAMO Academy, Alibaba GroupSenior Algorithm EngineerJan. 2021 - Jun. 2022
News
Selected Publications (view all )
Entity Enhancement for Implicit Discourse Relation Classification in the Biomedical Domain
Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP) 2021
We propose an entity-enhanced model for implicit discourse relation classification in the biomedical domain, leveraging entity information to improve relation detection.
Entity Enhancement for Implicit Discourse Relation Classification in the Biomedical Domain
Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP) 2021
We propose an entity-enhanced model for implicit discourse relation classification in the biomedical domain, leveraging entity information to improve relation detection.
Next Sentence Prediction helps Implicit Discourse Relation Classification within and across Domains
Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) 2019
We show that next sentence prediction, as used in BERT pre-training, can effectively help implicit discourse relation classification both within and across domains.
Next Sentence Prediction helps Implicit Discourse Relation Classification within and across Domains
Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) 2019
We show that next sentence prediction, as used in BERT pre-training, can effectively help implicit discourse relation classification both within and across domains.
Attention-based Bidirectional Long Short-term Memory Networks for Relation Classification
Peng Zhou, Wei Shi, Jun Tian, Zhenyu Qi, Bingchen Li, Hongwei Hao, Bo Xu
54th Annual Meeting of the Association for Computational Linguistics (ACL) 2016
We propose an attention-based bidirectional LSTM model for relation classification, which can capture the most important semantic information in a sentence.
Attention-based Bidirectional Long Short-term Memory Networks for Relation Classification
Peng Zhou, Wei Shi, Jun Tian, Zhenyu Qi, Bingchen Li, Hongwei Hao, Bo Xu
54th Annual Meeting of the Association for Computational Linguistics (ACL) 2016
We propose an attention-based bidirectional LSTM model for relation classification, which can capture the most important semantic information in a sentence.