Language Modeling with Shared Grammar

Yuyu Zhang, Le Song


Abstract
Sequential recurrent neural networks have achieved superior performance on language modeling, but overlook the structure information in natural language. Recent works on structure-aware models have shown promising results on language modeling. However, how to incorporate structure knowledge on corpus without syntactic annotations remains an open problem. In this work, we propose neural variational language model (NVLM), which enables the sharing of grammar knowledge among different corpora. Experimental results demonstrate the effectiveness of our framework on two popular benchmark datasets. With the help of shared grammar, our language model converges significantly faster to a lower perplexity on new training corpus.
Anthology ID:
P19-1437
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4442–4453
Language:
URL:
https://aclanthology.org/P19-1437
DOI:
10.18653/v1/P19-1437
Bibkey:
Cite (ACL):
Yuyu Zhang and Le Song. 2019. Language Modeling with Shared Grammar. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4442–4453, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Language Modeling with Shared Grammar (Zhang & Song, ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1437.pdf
Supplementary:
 P19-1437.Supplementary.pdf
Video:
 https://aclanthology.org/P19-1437.mp4
Data
Penn Treebank