Deep Contextualized Word Embeddings in Transition-Based and Graph-Based Dependency Parsing - A Tale of Two Parsers Revisited

Artur Kulmizev, Miryam de Lhoneux, Johannes Gontrum, Elena Fano, Joakim Nivre


Abstract
Transition-based and graph-based dependency parsers have previously been shown to have complementary strengths and weaknesses: transition-based parsers exploit rich structural features but suffer from error propagation, while graph-based parsers benefit from global optimization but have restricted feature scope. In this paper, we show that, even though some details of the picture have changed after the switch to neural networks and continuous representations, the basic trade-off between rich features and global optimization remains essentially the same. Moreover, we show that deep contextualized word embeddings, which allow parsers to pack information about global sentence structure into local feature representations, benefit transition-based parsers more than graph-based parsers, making the two approaches virtually equivalent in terms of both accuracy and error profile. We argue that the reason is that these representations help prevent search errors and thereby allow transition-based parsers to better exploit their inherent strength of making accurate local decisions. We support this explanation by an error analysis of parsing experiments on 13 languages.
Anthology ID:
D19-1277
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2755–2768
Language:
URL:
https://www.aclweb.org/anthology/D19-1277
DOI:
10.18653/v1/D19-1277
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D19-1277.pdf
Attachment:
 D19-1277.Attachment.zip