Discourse Analysis via Questions and Answers: Parsing Dependency Structures of Questions Under Discussion

Wei-Jen Ko, Yating Wu, Cutter Dalton, Dananjay Srinivas, Greg Durrett, Junyi Jessy Li

Abstract
Automatic discourse processing is bottlenecked by data: current discourse formalisms pose highly demanding annotation tasks involving large taxonomies of discourse relations, making them inaccessible to lay annotators. This work instead adopts the linguistic framework of Questions Under Discussion (QUD) for discourse analysis and seeks to derive QUD structures automatically. QUD views each sentence as an answer to a question triggered in prior context; thus, we characterize relationships between sentences as free-form questions, in contrast to exhaustive fine-grained taxonomies. We develop the first-of-its-kind QUD parser that derives a dependency structure of questions over full documents, trained using a large, crowdsourced question-answering dataset DCQA (Ko et al., 2022). Human evaluation results show that QUD dependency parsing is possible for language models trained with this crowdsourced, generalizable annotation scheme. We illustrate how our QUD structure is distinct from RST trees, and demonstrate the utility of QUD analysis in the context of document simplification. Our findings show that QUD parsing is an appealing alternative for automatic discourse processing.
Anthology ID:
2023.findings-acl.710
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11181–11195
Language:
URL:
https://aclanthology.org/2023.findings-acl.710
DOI:
10.18653/v1/2023.findings-acl.710
Bibkey:
Cite (ACL):
Wei-Jen Ko, Yating Wu, Cutter Dalton, Dananjay Srinivas, Greg Durrett, and Junyi Jessy Li. 2023. Discourse Analysis via Questions and Answers: Parsing Dependency Structures of Questions Under Discussion. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11181–11195, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Discourse Analysis via Questions and Answers: Parsing Dependency Structures of Questions Under Discussion (Ko et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.findings-acl.710.pdf
PDF Search