New York University

Hello. I am a third-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 was a research intern at Google Brain.

Research

Primary research subfields: text generation (including machine translation), structured prediction, and language understanding.

Publications (2021-)

AgreeSum: Agreement-Oriented Multi-Document Summarization
Richard Yuanzhe Pang*, Adam D. Lelkes*, Vinh Q. Tran*, Cong Yu
In Findings of ACL 2021
[paper] [abstract] [data] [short video] [bibtex]

Comparing Test Sets with Item Response Theory
Clara Vania*, Phu Mon Htut*, William Huang*, Dhara Mungra, Richard Yuanzhe Pang, Jason Phang, Haokun Liu, Kyunghyun Cho, Samuel R. Bowman
In Proceedings of ACL 2021
[paper] [abstract] [code] [bibtex]

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] [slides] [code] [bibtex]

Publications (-2020)

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] [my slides] [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
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]

More info: [semantic scholar] [google scholar] [dblp] [abbreviations]

Presentations

External presentations

  • Talk titled Text Generation by Learning from Demonstrations; Samsung workshop; June 2021 [based on this slide deck]
  • Talk on structured prediction; Bank of New York Mellon; September 2020 [based on this slide deck]
  • Talk titled Text Generation by Offline RL; Google Research New York; July 2020
  • Poster presentation on Learning Criteria and Evaluation Metrics for Textual Transfer between Non-Parallel Corpora; NAACL 2019 NeuralGen workshop in Minneapolis, USA; June 2019
  • Talk titled Learning Approximate Inference Networks and Structured Prediction Energy Networks; Midwest Speech and Language Days (MSLD) 2019 in Chicago, USA; May 2019
  • Poster presentation on Learning Criteria and Evaluation Metrics for Textual Transfer between Non-Parallel Corpora; UChicago STEM Research Symposium in Chicago, USA; October 2018

Conference presentations with associated proceeding papers

  • 5-min talk and poster presentation on Text Generation by Learning from Demonstrations; ICLR 2021; May 2021 [poster]
  • Poster presentation and lightning talk on The Daunting Task of Real-World Textual Style Transfer Auto-Evaluation; EMNLP 2019 WNGT workshop (poster) and W-NUT workshop (lightning talk) in Hong Kong, China; November 2019 [poster]
  • Poster presentation on Unsupervised Evaluation Metrics and Learning Criteria for Non-Parallel Textual Transfer; EMNLP 2019 WNGT workshop in Hong Kong, China; November 2019 [poster]

Other research activities

As a reviewer / program committee member

  • ACL (2021), ACL Rolling Review (10/2021), EMNLP (2021), ICLR (2022), NeurIPS (2021)
  • Workshops: NILLI (at EMNLP 2021)

Teaching

At New York University
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




Last updated: October 27, 2021. Contact: My NYU office is at 60 5th Ave. Get in touch at yzpang at _ dot edu (where _ is nyu or uchicago)!