Weakly Supervised Headline Dependency Parsing

Adrian Benton, Tianze Shi, Ozan İrsoy, Igor Malioutov


Abstract
English news headlines form a register with unique syntactic properties that have been documented in linguistics literature since the 1930s. However, headlines have received surprisingly little attention from the NLP syntactic parsing community. We aim to bridge this gap by providing the first news headline corpus of Universal Dependencies annotated syntactic dependency trees, which enables us to evaluate existing state-of-the-art dependency parsers on news headlines. To improve English news headline parsing accuracies, we develop a projection method to bootstrap silver training data from unlabeled news headline-article lead sentence pairs. Models trained on silver headline parses demonstrate significant improvements in performance over models trained solely on gold-annotated long-form texts. Ultimately, we find that, although projected silver training data improves parser performance across different news outlets, the improvement is moderated by constructions idiosyncratic to outlet.
Anthology ID:
2022.findings-emnlp.487
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6520–6535
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.487
DOI:
10.18653/v1/2022.findings-emnlp.487
Bibkey:
Cite (ACL):
Adrian Benton, Tianze Shi, Ozan İrsoy, and Igor Malioutov. 2022. Weakly Supervised Headline Dependency Parsing. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6520–6535, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Weakly Supervised Headline Dependency Parsing (Benton et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.487.pdf