The Importance of Category Labels in Grammar Induction with Child-directed Utterances

Lifeng Jin, William Schuler


Abstract
Recent progress in grammar induction has shown that grammar induction is possible without explicit assumptions of language specific knowledge. However, evaluation of induced grammars usually has ignored phrasal labels, an essential part of a grammar. Experiments in this work using a labeled evaluation metric, RH, show that linguistically motivated predictions about grammar sparsity and use of categories can only be revealed through labeled evaluation. Furthermore, depth-bounding as an implementation of human memory constraints in grammar inducers is still effective with labeled evaluation on multilingual transcribed child-directed utterances.
Anthology ID:
2020.iwpt-1.15
Volume:
Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies
Month:
July
Year:
2020
Address:
Online
Editors:
Gosse Bouma, Yuji Matsumoto, Stephan Oepen, Kenji Sagae, Djamé Seddah, Weiwei Sun, Anders Søgaard, Reut Tsarfaty, Dan Zeman
Venue:
IWPT
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
145–150
Language:
URL:
https://aclanthology.org/2020.iwpt-1.15
DOI:
10.18653/v1/2020.iwpt-1.15
Bibkey:
Cite (ACL):
Lifeng Jin and William Schuler. 2020. The Importance of Category Labels in Grammar Induction with Child-directed Utterances. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages 145–150, Online. Association for Computational Linguistics.
Cite (Informal):
The Importance of Category Labels in Grammar Induction with Child-directed Utterances (Jin & Schuler, IWPT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.iwpt-1.15.pdf
Video:
 http://slideslive.com/38929682
Data
Penn Treebank