Rob Voigt


2023

pdf bib
Large Language Models Are Partially Primed in Pronoun Interpretation
Suet-Ying Lam | Qingcheng Zeng | Kexun Zhang | Chenyu You | Rob Voigt
Findings of the Association for Computational Linguistics: ACL 2023

While a large body of literature suggests that large language models (LLMs) acquire rich linguistic representations, little is known about whether they adapt to linguistic biases in a human-like way. The present study probes this question by asking whether LLMs display human-like referential biases using stimuli and procedures from real psycholinguistic experiments. Recent psycholinguistic studies suggest that humans adapt their referential biases with recent exposure to referential patterns; closely replicating three relevant psycholinguistic experiments from Johnson & Arnold (2022) in an in-context learning (ICL) framework, we found that InstructGPT adapts its pronominal interpretations in response to the frequency of referential patterns in the local discourse, though in a limited fashion: adaptation was only observed relative to syntactic but not semantic biases. By contrast, FLAN-UL2 fails to generate meaningful patterns. Our results provide further evidence that contemporary LLMs discourse representations are sensitive to syntactic patterns in the local context but less so to semantic patterns. Our data and code are available at https://github.com/zkx06111/llm_priming.

pdf bib
Language of Bargaining
Mourad Heddaya | Solomon Dworkin | Chenhao Tan | Rob Voigt | Alexander Zentefis
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Leveraging an established exercise in negotiation education, we build a novel dataset for studying how the use of language shapes bilateral bargaining. Our dataset extends existing work in two ways: 1) we recruit participants via behavioral labs instead of crowdsourcing platforms and allow participants to negotiate through audio, enabling more naturalistic interactions; 2) we add a control setting where participants negotiate only through alternating, written numeric offers. Despite the two contrasting forms of communication, we find that the average agreed prices of the two treatments are identical. But when subjects can talk, fewer offers are exchanged, negotiations finish faster, the likelihood of reaching agreement rises, and the variance of prices at which subjects agree drops substantially. We further propose a taxonomy of speech acts in negotiation and enrich the dataset with annotated speech acts. We set up prediction tasks to predict negotiation success and find that being reactive to the arguments of the other party is advantageous over driving the negotiation.

2019

pdf bib
Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings
Dorottya Demszky | Nikhil Garg | Rob Voigt | James Zou | Jesse Shapiro | Matthew Gentzkow | Dan Jurafsky
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

We provide an NLP framework to uncover four linguistic dimensions of political polarization in social media: topic choice, framing, affect and illocutionary force. We quantify these aspects with existing lexical methods, and propose clustering of tweet embeddings as a means to identify salient topics for analysis across events; human evaluations show that our approach generates more cohesive topics than traditional LDA-based models. We apply our methods to study 4.4M tweets on 21 mass shootings. We provide evidence that the discussion of these events is highly polarized politically and that this polarization is primarily driven by partisan differences in framing rather than topic choice. We identify framing devices, such as grounding and the contrasting use of the terms “terrorist” and “crazy”, that contribute to polarization. Results pertaining to topic choice, affect and illocutionary force suggest that Republicans focus more on the shooter and event-specific facts (news) while Democrats focus more on the victims and call for policy changes. Our work contributes to a deeper understanding of the way group divisions manifest in language and to computational methods for studying them.

2018

pdf bib
Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)
Darja Fišer | Ruihong Huang | Vinodkumar Prabhakaran | Rob Voigt | Zeerak Waseem | Jacqueline Wernimont
Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)

pdf bib
RtGender: A Corpus for Studying Differential Responses to Gender
Rob Voigt | David Jurgens | Vinodkumar Prabhakaran | Dan Jurafsky | Yulia Tsvetkov
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Socially Responsible NLP
Yulia Tsvetkov | Vinodkumar Prabhakaran | Rob Voigt
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorial Abstracts

As language technologies have become increasingly prevalent, there is a growing awareness that decisions we make about our data, methods, and tools are often tied up with their impact on people and societies. This tutorial will provide an overview of real-world applications of language technologies and the potential ethical implications associated with them. We will discuss philosophical foundations of ethical research along with state of the art techniques. Through this tutorial, we intend to provide the NLP researcher with an overview of tools to ensure that the data, algorithms, and models that they build are socially responsible. These tools will include a checklist of common pitfalls that one should avoid (e.g., demographic bias in data collection), as well as methods to adequately mitigate these issues (e.g., adjusting sampling rates or de-biasing through regularization). The tutorial is based on a new course on Ethics and NLP developed at Carnegie Mellon University.

pdf bib
Proceedings of ACL 2018, Student Research Workshop
Vered Shwartz | Jeniya Tabassum | Rob Voigt | Wanxiang Che | Marie-Catherine de Marneffe | Malvina Nissim
Proceedings of ACL 2018, Student Research Workshop

2015

pdf bib
The Users Who Say ‘Ni’: Audience Identification in Chinese-language Restaurant Reviews
Rob Voigt | Dan Jurafsky
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

2014

pdf bib
Two Knives Cut Better Than One: Chinese Word Segmentation with Dual Decomposition
Mengqiu Wang | Rob Voigt | Christopher D. Manning
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2013

pdf bib
Tradition and Modernity in 20th Century Chinese Poetry
Rob Voigt | Dan Jurafsky
Proceedings of the Workshop on Computational Linguistics for Literature

pdf bib
Feature-Rich Phrase-based Translation: Stanford University’s Submission to the WMT 2013 Translation Task
Spence Green | Daniel Cer | Kevin Reschke | Rob Voigt | John Bauer | Sida Wang | Natalia Silveira | Julia Neidert | Christopher D. Manning
Proceedings of the Eighth Workshop on Statistical Machine Translation

2012

pdf bib
Towards a Literary Machine Translation: The Role of Referential Cohesion
Rob Voigt | Dan Jurafsky
Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature