About

I am currently on the Bard Extensions team at Google, where I work on data collection, data augmentation, and fine-tuning LLMs for tool use and code generation.

Previously, I was on the Assistant team at Google, where I worked on semantic parsing. I improved the quality of our neural models and drove changes to better pre-training for multi-lingual models and distillation from LLMs. I also made academic contributions in churn reduction via distillation, non-autoregressive semantic parsing, and zero-shot multi-lingual parsing.

I did my PhD in Computer Science at Columbia University, working under Professor Kathleen McKeown on Natural Language Processing. My thesis focused on understanding effective counter-arguments and my research contributions were in the areas of discourse, argumentation, and persuasion. Some of my projects can be found on GitHub, including work on fact-checking, argument generation, and identifying argumentative components and their semantic types.

In a prior life, I worked for the Department of Defense as a cryptanalytic developer.

Selected Publications


Christopher Hidey* and Sarthak Jauhari*.
"Compute-Efficient Churn Reduction for Conversational Agents."
In Proceedings of EMNLP 2023: Industry Track.
[pdf and bibtex]

William Held, Christopher Hidey, Fei Liu, Eric Zhu, Rahul Goel, Diyi Yang, Rushin Shah.
"DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue."
In Proceedings of ACL 2023.
[pdf and bibtex]

Geunseob Oh, Rahul Goel, Christopher Hidey, Shachi Paul, Aditya Gupta, Pararth Shah, Rushin Shah.
"Diverse Top-K Decoding for Non-Autoregressive Semantic Parsing via Intent Conditioning."
In Proceedings of COLING 2022.
[pdf and bibtex]

Christopher Hidey, Fei Liu, Rahul Goel.
"Reducing Model Churn: Stable Re-training of Conversational Agents."
In Proceedings of SIGDIAL 2022.
Best Paper
[pdf and bibtex] [code and data] [talk]

Tuhin Chakrabarty, Christopher Hidey, Smaranda Muresan.
"ENTRUST: Argument Reframing with Language Models and Entailment."
In Proceedings of NAACL 2021.
[pdf and bibtex] [code and data]

Christopher Hidey, Tuhin Chakrabarty, Tariq Alhindi, Siddharth Varia, Kriste Krstovski, Mona Diab and Smaranda Muresan.
"DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking."
In Proceedings of ACL 2020.
[pdf, bibtex, data, and talk] [code] [slides]

Tuhin Chakrabarty, Christopher Hidey, Smaranda Muresan, Kathleen McKeown, Alyssa Hwang.
"AMPERSAND: Argument Mining for PERSuAsive oNline Discussions."
In Proceedings of EMNLP 2019.
[pdf and bibtex] [code] [data] [slides]

Siddharth Varia, Christopher Hidey, and Tuhin Chakrabarty.
"Discourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks."
In Proceedings of SIGDIAL 2019.
[pdf and bibtex] [code] [slides]

Christopher Hidey and Kathleen McKeown.
"Fixed That for You: Generating Contrastive Claims with Semantic Edits."
In Proceedings of NAACL-HLT 2019.
[pdf and bibtex] [code] [poster]

Tuhin Chakrabarty, Christopher Hidey, and Kathleen McKeown.
"IMHO Fine-Tuning Improves Claim Detection."
In Proceedings of NAACL-HLT 2019.
[pdf and bibtex] [slides]

Christopher Hidey and Kathleen McKeown.
"Persuasive Influence Detection: The Role of Argument Sequencing."
In Proceedings of AAAI 2018.
[pdf] [code] [slides]

Christopher Hidey, Elena Musi, Alyssa Hwang, Smaranda Muresan, Kathleen McKeown.
"Analyzing the Semantic Types of Claims and Premises in an Online Persuasive Forum."
In Proceedings of the 4th Workshop on Argument Mining. EMNLP. 2017.
[pdf and bibtex] [data] [slides]

Christopher Hidey and Kathleen McKeown.
"Identifying Causal Relations Using Parallel Wikipedia Articles."
In Proceedings of ACL 2016.
[pdf and bibtex] [code] [talk]

Contact

My first name (short version) and last name, at either google or gmail.
[Linked In]
[Github]
[Google Scholar]
[Research at Google]