Research Interests

Discourse Relation Parsing, Sentiment Analysis, Generation, Relation Extraction, Deep Learning.


Education

July, 2016 - October, 2020
Ph.D Candidate, Department of Computational Linguistics and Phonetics, Saarland University, Saarbrücken, Germany.
Advisor: Prof. Dr. Vera Demberg.

Sept., 2013 - June, 2016
M.Sc, Computer Science, Institute of Automation, Chinese Academy of Sciences, Beijing, China.
Advisor: Prof. Dr. Hongwei Hao and Prof. Dr. Bo Xu

Sept., 2008 - June, 2012
B.Eng, Automation, Department of Power and Mechanical Engineering, Wuhan University, Hubei, China.


Publications

Next Sentence Prediction helps Implicit Discourse Relation Classification within and across Domains. [paper]
Wei Shi and Vera Demberg
In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019, Poster), November 3-7, 2019, Hong Kong, China

A Hybrid Model for Globally Coherent Story Generation. [paper]
Fangzhou Zhai, Vera Demberg, Pavel Shkadzko, Wei Shi and Asad Sayeed
In Proceedings of the 2nd workshop of Storytelling (StoryNLP@ACL2019, Oral), page 34-45, Aug 1, 2019, Florence, Italy

Acquiring Annotated Data with Cross-lingual Explicitation for Implicit Discourse Relation Classification. [paper]
Wei Shi, Frances Yung and Vera Demberg
In Proceedings of Discourse Relation Parsing and Treebanking (DISRPT@NAACL-2019, Oral), page 12-21, June 6, 2019, Minneapolis, USA

Learning to Explicitate Connectives with Seq2Seq Network for Implicit Discourse Relation Classification. [paper]
Wei Shi and Vera Demberg
In Proceedings of the 13th International Conference on Computational Semantics (IWCS-2019, Oral), page 188-199, May 23-27, 2019, Gothenburg, Sweden

Using Explicit Discourse Relation Connectives in Translation for Implicit Discourse Relation Classification. [paper] [data]
Wei Shi, Frances Yung, Raphael Rubino and Vera Demberg
In Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP-2017, Oral), page 484-495, Novermber 27- December 1, 2017, Taipei, Taiwan

On the Need of Cross Validation for Discourse Relation Classification. [paper]
Wei Shi and Vera Demberg
In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL-2017, Poster), page 150-156, April 3-7, 2017, Valencia, Spain.

Attention-based Bidirectional Long Short-term Memory Networks for Relation Classification. [paper]
Peng Zhou, Wei Shi, Jun Tian, Zhenyu Qi, Bingchen Li, Hongwei Hao, and Bo Xu.
In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL-2016, Poster), page 207-212, August 07-12, 2016, Berlin, Germany.


Professional Activities

PC member of IEEE TCSS, CoNLL-2018, 2019, NAACL-HLT-2019, ACL-2019, 2020, AACL-IJCNLP 2020 etc.






Last updated: 14-Aug-2019