This is not the latest version of this item. The latest version can be found here.
Working Hard or Hardly Working: Challenges of Integrating Typology into Neural Dependency Parsers
Name
D19-1574.pdf
Description
Published version
Size
340.3 KB
Format
Adobe PDF
Checksum (MD5)
099607273beeb5cfedfc9343c4c38054
Author(s)
Fisch, Adam
Guo, Jiang
Barzilay, Regina
Date Issued
November 2019
Journal
EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference
Publisher
Association for Computational Linguistics
Citation
Fisch, Adam, Guo, Jiang and Barzilay, Regina. 2019. "Working Hard or Hardly Working: Challenges of Integrating Typology into Neural Dependency Parsers." EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference.
Version
Final published version
Abstract
© 2019 Association for Computational Linguistics This paper explores the task of leveraging typology in the context of cross-lingual dependency parsing. While this linguistic information has shown great promise in preneural parsing, results for neural architectures have been mixed. The aim of our investigation is to better understand this state-of-the-art. Our main findings are as follows: 1) The benefit of typological information is derived from coarsely grouping languages into syntactically-homogeneous clusters rather than from learning to leverage variations along individual typological dimensions in a compositional manner; 2) Typology consistent with the actual corpus statistics yields better transfer performance; 3) Typological similarity is only a rough proxy of cross-lingual transferability with respect to parsing.1.
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
10.18653/V1/D19-1574
