NAACL 2024findings1 citations
Interpreting Answers to Yes-No Questions in Dialogues from Multiple Domains
Zijie Wang, Farzana Rashid, Eduardo Blanco
Abstract
People often answer yes-no questions without explicitly saying yes, no, or similar polar key-words. Figuring out the meaning of indirectanswers is challenging, even for large language models. In this paper, we investigate this problem working with dialogues from multiple domains. We present new benchmarks in three diverse domains: movie scripts, tennis interviews, and airline customer service. We present an approach grounded on distant supervision and blended training to quickly adapt to a new dialogue domain. Experimental results show that our approach is never detrimental and yields F1 improvements as high as 11-34%.
BibTeX
@inproceedings{wang-etal-2024-interpreting,
title = "Interpreting Answers to Yes-No Questions in Dialogues from Multiple Domains",
author = "Wang, Zijie and
Rashid, Farzana and
Blanco, Eduardo",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.136/",
doi = "10.18653/v1/2024.findings-naacl.136",
pages = "2111--2128"
}