Zero-shot Script Parsing

Fangzhou Zhai, Vera Demberg, Alexander Koller


Abstract
Script knowledge is useful to a variety of NLP tasks. However, existing resources only cover a small number of activities, limiting its practical usefulness. In this work, we propose a zero-shot learning approach to script parsing, the task of tagging texts with scenario-specific event and participant types, which enables us to acquire script knowledge without domain-specific annotations. We (1) learn representations of potential event and participant mentions by promoting cluster consistency according to the annotated data; (2) perform clustering on the event / participant candidates from unannotated texts that belongs to an unseen scenario. The model achieves 68.1/74.4 average F1 for event / participant parsing, respectively, outperforming a previous CRF model that, in contrast, has access to scenario-specific supervision. We also evaluate the model by testing on a different corpus, where it achieved 55.5/54.0 average F1 for event / participant parsing.
Anthology ID:
2022.coling-1.356
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4049–4060
Language:
URL:
https://aclanthology.org/2022.coling-1.356
DOI:
Bibkey:
Cite (ACL):
Fangzhou Zhai, Vera Demberg, and Alexander Koller. 2022. Zero-shot Script Parsing. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4049–4060, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Zero-shot Script Parsing (Zhai et al., COLING 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2022.coling-1.356.pdf
Data
MCScript