PARROT: Zero-Shot Narrative Reading Comprehension via Parallel Reading

Chao Zhao, Anvesh Vijjini, Snigdha Chaturvedi


Abstract
Narrative comprehension is a challenging task that requires a deep understanding of the foundational elements of narratives. Acquiring this skill requires extensive annotated data. To mitigate the burden of data annotation, we present Parrot, a zero-shot approach for narrative reading comprehension through parallel reading, which involves two parallel narratives that tell the same story. By leveraging one narrative as a source of supervision signal to guide the understanding of the other, Parrot abstracts the textual content and develops genuine narrative understanding. Evaluation conducted on two narrative comprehension benchmarks demonstrates that Parrot surpasses previous zero-shot approaches and achieves comparable performance to fully supervised models. The code will be available at https://github.com/zhaochaocs/Parrot.
Anthology ID:
2023.findings-emnlp.895
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13413–13424
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.895
DOI:
10.18653/v1/2023.findings-emnlp.895
Bibkey:
Cite (ACL):
Chao Zhao, Anvesh Vijjini, and Snigdha Chaturvedi. 2023. PARROT: Zero-Shot Narrative Reading Comprehension via Parallel Reading. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13413–13424, Singapore. Association for Computational Linguistics.
Cite (Informal):
PARROT: Zero-Shot Narrative Reading Comprehension via Parallel Reading (Zhao et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-emnlp.895.pdf