Challenges to Open-Domain Constituency Parsing
Sen Yang, Leyang Cui, Ruoxi Ning, Di Wu, Yue Zhang
Abstract
Neural constituency parsers have reached practical performance on news-domain benchmarks. However, their generalization ability to other domains remains weak. Existing findings on cross-domain constituency parsing are only made on a limited number of domains. Tracking this, we manually annotate a high-quality constituency treebank containing five domains. We analyze challenges to open-domain constituency parsing using a set of linguistic features on various strong constituency parsers. Primarily, we find that 1) BERT significantly increases parsers’ cross-domain performance by reducing their sensitivity on the domain-variant features.2) Compared with single metrics such as unigram distribution and OOV rate, challenges to open-domain constituency parsing arise from complex features, including cross-domain lexical and constituent structure variations.
BibTeX
@inproceedings{yang-etal-2022-challenges,
title = "Challenges to Open-Domain Constituency Parsing",
author = "Yang, Sen and
Cui, Leyang and
Ning, Ruoxi and
Wu, Di and
Zhang, Yue",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.11/",
doi = "10.18653/v1/2022.findings-acl.11",
pages = "112--127"
}