Steven Feng

I am a graduate student at Carnegie Mellon University (CMU). Previously, I was an undergraduate student at the University of Waterloo and Wilfrid Laurier University. I have a strong passion for data science and machine learning, particularly natural language processing (NLP).

I have extensive research experience and have published at major conferences such as EMNLP and AAAI. I am also an Honorable Mention for the Jessie W.H. Zou Memorial Award and CRA Outstanding Undergraduate Researcher Award. My present interests are mainly in language generation, data augmentation, and dialogue agents.

I am currently working with the Language Technologies Institute (LTI) at CMU on research projects involving controllable generation, data augmentation, and semantics. Previously, I worked with with numerous University of Waterloo professors, including Dr. Jesse Hoey on dialogue agents and semantics and Dr. Pascal Poupart on robust embeddings and machine translation.

Other than research, I enjoy machine learning projects and hackathons. In my free time, I like gaming, playing the piano, and table tennis.

Email  /  CV (Oct. 2020)  /  Google Scholar  /  LinkedIn  /  Twitter  /  GitHub

profile photo

Publications

GenAug: Data Augmentation for Finetuning Text Generators
Steven Y. Feng*, Varun Gangal*, Dongyeop Kang, Teruko Mitamura, Eduard Hovy
Accepted to EMNLP 2020 Deep Learning Inside Out (DeeLIO) Workshop (long paper)
Abstract / Bibtex / Talk / Presentation Slides / GitHub

ALOHA: Artificial Learning of Human Attributes for Dialogue Agents
Aaron W. Li, Veronica Jiang*, Steven Y. Feng*, Julia Sprague, Wei Zhou, Jesse Hoey
Proceedings of AAAI Conference on Artificial Intelligence 2020 (20.6% acceptance rate) (long paper) (oral)
Abstract / Bibtex / Talk / Presentation Slides / Poster / GitHub

Keep Calm and Switch On! Preserving Sentiment and Fluency in Semantic Text Exchange
Steven Y. Feng*, Aaron W. Li*, Jesse Hoey
Proceedings of Empirical Methods in Natural Language Processing (EMNLP) 2019 (23.8% acceptance rate) (long paper)
Abstract / Bibtex / News Article / Poster / GitHub

* Equal Contribution

Site Template