Transition-based Bubble Parsing: Improvements on Coordination Structure Prediction

Tianze Shi, Lillian Lee


Abstract
We propose a transition-based bubble parser to perform coordination structure identification and dependency-based syntactic analysis simultaneously. Bubble representations were proposed in the formal linguistics literature decades ago; they enhance dependency trees by encoding coordination boundaries and internal relationships within coordination structures explicitly. In this paper, we introduce a transition system and neural models for parsing these bubble-enhanced structures. Experimental results on the English Penn Treebank and the English GENIA corpus show that our parsers beat previous state-of-the-art approaches on the task of coordination structure prediction, especially for the subset of sentences with complex coordination structures.
Anthology ID:
2021.acl-long.557
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7167–7182
Language:
URL:
https://aclanthology.org/2021.acl-long.557
DOI:
10.18653/v1/2021.acl-long.557
Bibkey:
Cite (ACL):
Tianze Shi and Lillian Lee. 2021. Transition-based Bubble Parsing: Improvements on Coordination Structure Prediction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 7167–7182, Online. Association for Computational Linguistics.
Cite (Informal):
Transition-based Bubble Parsing: Improvements on Coordination Structure Prediction (Shi & Lee, ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2021.acl-long.557.pdf
Video:
 https://preview.aclanthology.org/ingest-acl-2023-videos/2021.acl-long.557.mp4
Code
 tzshi/bubble-parser-acl21
Data
GENIAPenn TreebankUniversal Dependencies