Neural Reranking for Dependency Parsing: An Evaluation

Bich-Ngoc Do, Ines Rehbein


Abstract
Recent work has shown that neural rerankers can improve results for dependency parsing over the top k trees produced by a base parser. However, all neural rerankers so far have been evaluated on English and Chinese only, both languages with a configurational word order and poor morphology. In the paper, we re-assess the potential of successful neural reranking models from the literature on English and on two morphologically rich(er) languages, German and Czech. In addition, we introduce a new variation of a discriminative reranker based on graph convolutional networks (GCNs). We show that the GCN not only outperforms previous models on English but is the only model that is able to improve results over the baselines on German and Czech. We explain the differences in reranking performance based on an analysis of a) the gold tree ratio and b) the variety in the k-best lists.
Anthology ID:
2020.acl-main.379
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4123–4133
Language:
URL:
https://aclanthology.org/2020.acl-main.379
DOI:
10.18653/v1/2020.acl-main.379
Bibkey:
Cite (ACL):
Bich-Ngoc Do and Ines Rehbein. 2020. Neural Reranking for Dependency Parsing: An Evaluation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4123–4133, Online. Association for Computational Linguistics.
Cite (Informal):
Neural Reranking for Dependency Parsing: An Evaluation (Do & Rehbein, ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.379.pdf
Video:
 http://slideslive.com/38929031