Sean Welleck's Home Page

I am a PhD Student at New York University, advised by Kyunghyun Cho and Zheng Zhang.
My research focuses on deep learning and structured prediction, with applications in natural language processing.
I interned at Facebook AI Research in Summer 2018 and Summer 2019.

News

• Our paper on consistency of language models was accepted to EMNLP 2020.
• TA for [DS-GA 1008 Fall 2020] Deep Learning.
• New paper on MLE-guided parameter search.
• Presented our paper on unlikelihood for dialogue at ACL 2020.
• Our paper on unlikelihood training was accepted to ICLR 2020.
• TA for [CSCI-UA.0473 Spring 2020] Introduction to Machine Learning.
• Talk at RANLP 2019 presenting our paper on dependency parsing as sequential set generation.
• Presented our paper on reducing contradictions in dialogue with natural language inference at ACL 2019.
• Presented our paper on generating text in learned orders at ICML 2019.

Papers

• S. Welleck, K. Cho. MLE-guided parameter search for task loss minimization in neural sequence modeling.
  arXiv pre-print 2020.
• S. Welleck*, I. Kulikov*, J. Kim, R. Pang, K. Cho. Consistency of a Recurrent Language Model With Respect to Incomplete Decoding.
  Empirical Methods in Natural Language Processing (EMNLP) 2020.
• E. Mansimov, A. Wang, S. Welleck, K. Cho. A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models.
  arXiv pre-print 2020.
  [code]
• M. Li, S. Roller, I. Kulikov, S. Welleck, Y.L. Boureau, K. Cho, J. Weston. Making Inconsistent Dialogue Unlikely with Unlikelihood Training.
  58th Annual Meeting of the Association for Computational Linguistics, (ACL) 2020.
• S. Welleck*, I. Kulikov*, S. Roller, E. Dinan, K. Cho, J. Weston. Neural Text Generation with Unlikelihood Training.
  8th International Conference on Learning Representations (ICLR) 2020.
  [code]
• S. Welleck, K. Brantley, H. Daume III, K. Cho. Non-Monotonic Sequential Text Generation.
  36th International Conference on Machine Learning (ICML) 2019.
  [code] [slides] [poster]
• S. Welleck, K. Cho. Sequential Graph Dependency Parser.
  Recent Advances in Natural Language Processing (RANLP) 2019.
  [slides]
• S. Welleck, J. Weston, A. Szlam, K. Cho. Dialogue Natural Language Inference.
  57th Annual Meeting of the Association for Computational Linguistics, (ACL) 2019.
  [dataset][poster][press]
• S. Welleck, Z. Yao, Y. Gai, J. Mao, Z. Zhang, K. Cho. Loss Functions for Multiset Prediction.
  Neural Information Processing Systems 31 (NeurIPS) 2018.
  NVIDIA AI Labs Pioneering Research Award 2018.
  [poster]
• S. Welleck, J. Mao, K. Cho, Z. Zhang. Saliency-based Sequential Image Attention with Multiset Prediction.
  Neural Information Processing Systems 30 (NIPS) 2017.
  NVIDIA AI Labs Pioneering Research Award 2017.
  [poster][press]
• S. Welleck. Efficient AUC Optimization for Information Ranking Applications.
  European Conference on Information Retrieval (ECIR) 2016.

Past

• Facebook, AI Research Team (FAIR), May. 2019 - Sep. 2019
• Facebook, AI Research Team (FAIR), May. 2018 - Jan. 2019
• Primer AI, Feb. 2016 - Aug. 2016
• IBM, Sep. 2014 - Feb. 2016
• University of Pennsylvania (Computer Science, MSE), May. 2013 - May. 2014
• University of Pennsylvania (Computer Science, BSE), Sep. 2009 - Feb. 2013