Hello. I am a second-year Ph.D. student in the Courant Institute of Mathematical Sciences at New York University. I am a member of the Machine Learning for Language (ML²) group (subset of the CILVR group). I am advised by Prof. He He and Prof. Kyunghyun Cho.
My research focuses on natural langauge processing and machine learning. Specifically, recent interests include text generation, neural machine translation, and structured prediction.
Prior to my Ph.D., I graduated from the University of Chicago in June 2019 (B.S. in mathematics and B.S. in computer science). In Chicago, my advisor was Prof. Kevin Gimpel at Toyota Technological Institute at Chicago (TTIC) and the University of Chicago. In Summer 2020, I was a research intern at Google Research New York; in Summer 2021, I will be a research intern at Google Brain.
Research
Primary research subfields: text generation, machine translation, structured prediction, language understanding.
Publications
Text Generation by Learning from Demonstrations
Richard Yuanzhe Pang, He He
In Proceedings of ICLR 2021
tl;dr: a high-precision-generation training objective to address the train/test objective mismatch and history mismatch
[paper] [abstract] [openreview] [poster] [5-min slides] [code] [bibtex]
Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
Lifu Tu, Richard Yuanzhe Pang, Kevin Gimpel
In Proceedings of EMNLP 2020 Workshop on Structured Prediction for NLP (SPNLP); spotlight paper
tl;dr: improving fast approximate+amortized inference for energy-based models in NLP structured prediction
[paper] [abstract] [bibtex]
Consistency of a Recurrent Language Model With Respect to Incomplete Decoding
Sean Welleck, Ilia Kulikov, Jaedeok Kim, Richard Yuanzhe Pang, Kyunghyun Cho
In Proceedings of EMNLP 2020
Also appearing in the non-archival DeepMath 2020
[paper] [abstract] [code] [bibtex]
ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation
Lifu Tu, Richard Yuanzhe Pang, Sam Wiseman, Kevin Gimpel
In Proceedings of ACL 2020
tl;dr: a "soft" form of knowledge distillation for non-autoregressive MT
[paper] [abstract] [code] [bibtex]
Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?
Yada Pruksachatkun, Jason Phang, Haokun Liu, Phu Mon Htut, Xiaoyi Zhang, Richard Yuanzhe Pang, Clara Vania, Katharina Kann, Samuel R. Bowman
In Proceedings of ACL 2020
[paper] [abstract] [bibtex]
Unsupervised Evaluation Metrics and Learning Criteria for Non-Parallel Textual Transfer
Richard Yuanzhe Pang, Kevin Gimpel
In Proceedings of EMNLP 2019 Workshop on Neural Generation and Translation (WNGT)
tl;dr: proposing more dimensions for textual transfer evaluation metrics, and losses that target them
[paper] [supplementals] [abstract] [poster] [bibtex]
The Daunting Task of Real-World Textual Style Transfer Auto-Evaluation
More info: [google scholar] [semantic scholar] [dblp] [abbreviations]
At New York University
Last updated: March 3, 2021. Get in touch at yzpang at _ dot edu (where _ is nyu or uchicago)!
Richard Yuanzhe Pang
Extended abstract in EMNLP 2019 Workshop on Neural Generation and Translation (WNGT); abstract in Proceedings of the Workshop on Noisy User-generated Text (W-NUT)
tl;dr: an opinion piece arguing that the research on textual style transfer and its evaluation are going astray
[paper] [abstract] [poster] [bibtex]
Presentations
Teaching
Fall 2020, Section Leader (in-person), DS-GA 1008: Deep Learning (Cho, LeCun) [syllabus]
At the University of Chicago
Spring 2017, Course Assistant, MATH 15910: Intro to Proofs in Analysis
Winter 2017, Course Assistant, MATH 15910: Intro to Proofs in Analysis [sol]
Winter 2017, Grader, CMSC 15200: Intro to Computer Science II
Autumn 2016, Teaching Assistant, MATH 15300: Calculus III