Emergence of Syntax Needs Minimal Supervision

Raphaël Bailly, Kata Gábor


Abstract
This paper is a theoretical contribution to the debate on the learnability of syntax from a corpus without explicit syntax-specific guidance. Our approach originates in the observable structure of a corpus, which we use to define and isolate grammaticality (syntactic information) and meaning/pragmatics information. We describe the formal characteristics of an autonomous syntax and show that it becomes possible to search for syntax-based lexical categories with a simple optimization process, without any prior hypothesis on the form of the model.
Anthology ID:
2020.acl-main.46
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
477–487
Language:
URL:
https://www.aclweb.org/anthology/2020.acl-main.46
DOI:
10.18653/v1/2020.acl-main.46
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.acl-main.46.pdf
Video:
 http://slideslive.com/38929115