About:

I am currently a research scientist at Google Deepmind. I am interested in projects for designing and evaluating NLP systems that are more knowledge-grounded, controllable, interactive, and capable of complex reasoning. I also am interested in postiive applications of NLP models for real-world challenges and the intersection of NLP and computational social science. In June 2020, I received a PhD from the University of Washington, advised by Prof. Yejin Choi. Before graduate school, I was an undergraduate student at University of Illinois at Urbana-Champaign.

I have also previously worked as an intern at MSR (working with Asli Celikyilmaz, summer 2019), a part-time research intern at the Allen Institute of Artificial Intelligence (the Mosaic project for commonsense reasoning, 2018-2019), an intern at FAIR (with Y-Lan Boureau, summer 2018) and an intern at Pacific Northwest National Laboratory (with Svitlana Volkova, summer 2016).

Recent Projects:

Attribution Metrics

Human evals of attribution in grounded model output

Data CL 2023 Paper

Attribution in Dialogue

The Begin Dataset: For meta-evaluation of attribution metrics on knowledge-grounded dialogue

Data TACL 2022 Paper

Navigating tradeoffs between attribution and specificity in dialogue

EACL 2024 Paper

Controllability with LMs

Increasing Faithfulness with Control Codes

ACL 2021 Paper

Phd Projects:

Social IQA Dataset

New benchmark for measuring models' ability to reason about social interactions

Project Page Paper

Grover: Defending against Fake News

Identifying neural fake news

Project Page Paper

Story Commonsense Dataset

Inferring changes in character motivations and emotional reactions in short commonsense narratives

Project Page ACL 2018 paper

Multilingual Connotation

Multilingual analysis of connotation over twitter.

Project Page ACL 2017 Short Paper

EmpatheticDialogues Dataset

New dataset and task for empathetic response generation

Project Page ACL 2019 paper

ATOMIC

Large-scale commonsense knowledge graph for if-then reasoning about events

Project Page AAAI 2019 paper

Event2Mind

Pragmatic inference of the intent and reactions of participants in events

Project Page ACL 2018 paper

Connotation Frames

Investigating predicate-specific lexicons for connotative relationships implied by word choice.

Project Page ACL 2016 paper

COMET

Commonsense Transformers for knowledge graph construction

Demo Page ACL 2019 paper

Power & Agency in Movies

Incorporating power and agency to connotation frame lexicon with analysis of gender bias in movies

Project Page EMNLP 2017 short paper

Fact-Checking

Linguistic analysis of subtle persuasive techniques to detect truth-bending

Project Page EMNLP 2017 short paper

Document-level Sentiment Inference with Social, Faction, and Discourse Context

Incorporating social theories to perform entity-entity sentiment inference at a document level.

Demo Page ACL 2016 Paper