Zhang, Wei

Wei Zhang is a research scentist at IBM T.J. Watson Research Center. He is broadly interested in artificial neural networks and natural language processing. He graduated from CMU in 2014. His recent interest is in explainable NLP, human-AI and AI-AI communication in dialogues and language games, and NLP applications to high-stake domains such as finance.

He recently proved for the first time that BERT can encode lexical semantics better than GloVe on a intrinsic evaluation using psycholinguistic data, help explaining why pre-trained Transformers are better encoders.

His recently served as a PC member for: ACL 2020, EMNLP 2020, NAACL 2021, EACL 2021, SLT 2021, NeurIPS 2020.

IBM Research Home
Semantic Scholar
Google Scholar

Selected Publications

Wei Zhang, Murray Campbell, Yang Yu, Sadhana Kumaravel. Circles are like Ellipses, or Ellipses are like Circles? Measuring the Degree of Asymmetry of Static and Contextual Word Embeddings and the Implications to Representation Learning. AAAI 2021

Zahra Ashktorab, James Johnson, Qian Pan, Wei Zhang, Casey Dugan. The Design and Development of Games with aPurpose for AI System. Workshop of Human And Machine in-the-Loop Evaluation and Learning Strategies, NeurIPS 2020

Katy Ilonka Gero, Zahra Ashktorab, Casey Dugan, Qian Pan, James Johnson, Werner Geyer, Maria Ruiz, Sarah Miller, David R Millen, Murray Campbell, Sadhana Kumaravel, Wei Zhang. Mental Models of AI Agents in a Cooperative Game Setting. CHI 2020 (Best Paper Award)

Shuohang Wang, Mo Yu, Xiaoxiao Guo, Zhiguo Wang, Tim Klinger, Wei Zhang, Shiyu Chang, Gerald Tesauro, Bowen Zhou, Jing Jiang. R $^ 3$: Reinforced Reader-Ranker for Open-Domain Question Answering. AAAI 2018

Shuohang Wang, Mo Yu, Jing Jiang, Wei Zhang, Xiaoxiao Guo, Shiyu Chang, Zhiguo Wang, Tim Klinger, Gerald Tesauro, Murray Campbell. Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering. ICLR 2018

Zhang, Wei, Bowen Zhou. Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization. arxiv. preprint arXiv:1709.06493 (2017).

Zhang, Wei*, Yang Yu*, Kazi Hasan, Mo Yu, Bing Xiang, Bowen Zhou. Dynamic Chunk Reader for Machine Reading Comprehension arxiv. preprint: arXiv:1610.09996 (2016) (* equal contribution)

Zhang, Wei, Yang Yu, Bowen Zhou. Structured Memory for Neural Turing Machines Reasoning, Memory and Attention Workshop. NIPS 2015 [slides]

Yu, Yang, Wei Zhang, Chung-Wei Hang, and Bowen Zhou. Empirical Study on Deep Learning Models for Question Answering. arXiv preprint arXiv:1510.07526 (2015).

Zhang, Wei, and Judith Gelernter. Geocoding location expressions in Twitter messages: A preference learning method. Journal of Spatial Information Science 2014, no. 9 (2014): 37-70.

Gelernter, Judith, and Wei Zhang. Cross-lingual geo-parsing for non-structured data. In Proceedings of the 7th Workshop on Geographic Information Retrieval, pp. 64-71. ACM, 2013.

Guo, Yuhang, Wanxiang Che, Yuxuan Hu, Wei Zhang, and Ting Liu. HIT-IR-WSD: A wsd system for english lexical sample task. In Proceedings of the ACL SemEval. (2007). (System won 1st place on SemEval 2007 Task 11)


"On Machine Reading Comprehension and Question Answering" [slides] at Harvard NLP Reading Group

"Structured Memory for Neural Turing Machines" [slides] on NIPS 2015 RAM workshop