Joint Morphological and Syntactic Analysis for Richly Inflected Languages

Bernd Bohnet, Joakim Nivre, Igor Boguslavsky, Richárd Farkas, Filip Ginter, Jan Hajič


Abstract
Joint morphological and syntactic analysis has been proposed as a way of improving parsing accuracy for richly inflected languages. Starting from a transition-based model for joint part-of-speech tagging and dependency parsing, we explore different ways of integrating morphological features into the model. We also investigate the use of rule-based morphological analyzers to provide hard or soft lexical constraints and the use of word clusters to tackle the sparsity of lexical features. Evaluation on five morphologically rich languages (Czech, Finnish, German, Hungarian, and Russian) shows consistent improvements in both morphological and syntactic accuracy for joint prediction over a pipeline model, with further improvements thanks to lexical constraints and word clusters. The final results improve the state of the art in dependency parsing for all languages.
Anthology ID:
Q13-1034
Volume:
Transactions of the Association for Computational Linguistics, Volume 1
Month:
Year:
2013
Address:
Cambridge, MA
Editors:
Dekang Lin, Michael Collins
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
415–428
Language:
URL:
https://aclanthology.org/Q13-1034
DOI:
10.1162/tacl_a_00238
Bibkey:
Cite (ACL):
Bernd Bohnet, Joakim Nivre, Igor Boguslavsky, Richárd Farkas, Filip Ginter, and Jan Hajič. 2013. Joint Morphological and Syntactic Analysis for Richly Inflected Languages. Transactions of the Association for Computational Linguistics, 1:415–428.
Cite (Informal):
Joint Morphological and Syntactic Analysis for Richly Inflected Languages (Bohnet et al., TACL 2013)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/Q13-1034.pdf