Hi, I’m Gin, a PhD student at University of Waterloo, supervised by Professor Jimmy Lin. Before coming to Canada, I spent four years at Rensselaer Polytechnic Institute and did research at Blender, supervised by Professor Heng Ji.
On a high level, I’m mainly interested in understanding and improving machine learning. Generalization and interpretability are two topics that I’m mostly enthusiastic about, from theory to applications. I also love information theory for its elegancy and how it connects to machine learning.
Besides machine learning, I also love food science and neuroscience.
- BlackBoxNLPHow Does BERT Rerank Passages? An Attribution Analysis with Information BottlenecksIn Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2021
- EMNLP2020Inserting Information Bottleneck for Attribution in TransformersIn Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings 2020
- EMNLP2020Document Ranking with a Pretrained Sequence-to-Sequence ModelIn Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings 2020
- ACL2019PaperRobot: Incremental Draft Generation of Scientific IdeasIn Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics 2019
- BEAChengyu cloze testIn Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications 2018