What’s New?

Feb 2021 Invited Talk at AAAI Workshop in Hybrid Artificial Intelligence
Feb 2021 Tutorial on Commonsense Knowledge Acquisition and Representation at AAAI 2021
Dec 2020 One new preprint posted to arXiv [1]
Dec 2020 Two papers accepted to AAAI 2021 [1, 2]
Nov 2020 Tutorial on Neural Language Generation at EMNLP 2020
Nov 2020 Invited Talk at UCSD Health Informatics Seminar
Nov 2020 Invited Talk at Stanford Cognitive Science Seminar
Oct 2020 One paper accepted to EMNLP 2020
Aug 2020 I’ve moved to Stanford!
July 2020 Tutorial on Commonsense Knowledge at ACL 2020
May 2020 One paper accepted to AKBC 2020. Best Paper Runner-up
Nov 2019 One paper accepted to AAAI 2020
Sep 2019 Talk at WeCNLP 2019
Aug 2019 Three papers accepted to EMNLP 2019 [1, 2, 3]
Jun 2019 Organized NeuralGen Workshop @ NAACL 2019
Apr 2019 COMET paper accepted to ACL 2019
Apr 2018 Two papers accepted to ACL 2018 [1, 2]
Feb 2018 Two papers accepted to NAACL 2018 [1, 2]
Jan 2018 One paper accepted to ICLR 2018
Dec 2017 Won an AI2 Key Scientific Challenges Award

Publications

(2021). Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answering. Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI).

PDF

(2020). Procedural Reading Comprehension with Attribute-Aware Context Flow. Proceedings of the 2nd Conference on Automated Knowledge Base Construction (AKBC). Best Paper Runner-up.

PDF

(2020). Commonsense Knowledge Base Completion with Structural and Semantic Context. Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI).

PDF

(2019). Counterfactual Story Reasoning and Generation. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP).

PDF Code Dataset

(2019). WIQA: A dataset for "What if..." reasoning over procedural text. Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP).

PDF Code Dataset Project

(2019). Be Consistent! Improving Procedural Text Comprehension using Label Consistency. Proceedings of the 17th Annual Meeting of the North American Association for Computational Linguistics (NAACL).

PDF Dataset Project

(2018). Simulating Action Dynamics with Neural Process Networks. Proceedings of the 6th International Conference for Learning Representations (ICLR).

PDF Dataset Poster Video

(2018). Discourse-Aware Neural Rewards for Coherent Text Generation. Proceedings of the 16th Annual Meeting of the North American Association for Computational Linguistics (NAACL).

PDF Dataset Poster

(2018). Deep Communicating Agents for Abstractive Summarization. Proceedings of the 16th Annual Meeting of the North American Association for Computational Linguistics (NAACL).

PDF Project Poster

(2018). Modeling Naive Psychology of Characters in Simple Commonsense Stories. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL).

PDF Code Dataset Project Slides

(2018). Learning to Write with Cooperative Discriminators. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL).

PDF Code Project Poster

(2016). Learning Prototypical Event Structure from Photo Albums. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL).

PDF Dataset Project Video

News & Media

Communications of the ACM. Seeking Artificial Common Sense (November 2020)

The Atlantic. The Easy Questions that Stump Computers (May 2020)

Quanta Magazine. Common Sense Comes Closer to Computers (April 2020)

New York Academy of Sciences. Can Researchers Create Commonsense Artificial Intelligence? (June 2019)

The Gradient. NLP’s generalization problem, and how researchers are tackling it (August 2018)

NLP Highlights Podcast. 54 - Simulating Action Dynamics with Neural Process Networks, with Antoine Bosselut (March 2018)

Projects

Neuro-symbolic Representations of Commonsense Knowledge

Machines must be able to represent relevant and correct commonsense for an unbounded set of situations. We explore how to capture this knowledge at scale.

Procedural Language Understanding with Commonsense Simulation

Understanding procedural text such as instructions or stories requires anticipating the implicit causal effects described by the events in the text, necessitating new classes of algorithms that can learn to simulate these effects directly.

Language Generation with Pragmatic Discriminator Networks

Content and style coherence of neural language generators deteriorates dramatically when generating long text. We design discriminator models that change language generation objectives to encourage long-term coherence.

Document Summarization with Discourse Understanding

Abstractive summarization requires understanding the latent discourse properties of how information is presented. We develop new approaches for integrating these inductive biases into summarization architectures.

Scientific Process Understanding

Scientific texts describe complex interactions between entities and use specific non-generalizable terminology. We explore methods for learning to understand this type of language.

Learning Prototypical Event Structure from Photo Albums

Activities and events in our lives are structural, be it a vacation, a camping trip, or a wedding. While individual details vary, there are characteristic patterns that are specific to each of these scenarios

Experience

 
 
 
 
 

Postdoctoral Researcher

Stanford University

Aug 2020 – Present
 
 
 
 
 

Student Researcher

Allen Institute for Artificial Intelligence (AI2)

Mar 2018 – Jul 2020 Washington
 
 
 
 
 

Student Researcher

Microsoft Research

Nov 2017 – Dec 2018 Washington
 
 
 
 
 

Research Intern

Microsoft Research

Jun 2017 – Sep 2017 Washington
 
 
 
 
 

PhD Student

Paul G. Allen School of Computer Science and Engineering, University of Washington

Sep 2014 – Aug 2020 Seattle, Washington