Typology-aware neural dependency parsing : challenges and directions
Author(s)
Fisch, Adam(Adam Joshua)![Thumbnail](/bitstream/handle/1721.1/128400/1203138358-MIT.pdf.jpg?sequence=4&isAllowed=y)
Download1203138358-MIT.pdf (526.4Kb)
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
Regina Barzilay.
Terms of use
Metadata
Show full item recordAbstract
This thesis explores the task of leveraging typology in the context of cross-lingual dependency parsing. While this linguistic information has shown great promise in pre-neural parsing, results for neural architectures have been mixed. The aim of the investigation put forth in this thesis 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. Code for the work in this thesis is available at https://github.com/ajfisch/TypologyParser.
Description
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, February, 2020 Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 39-41).
Date issued
2020Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.