Simple Hardware-Efficient PCFGs with Independent Left and Right Productions

Wei Liu, Songlin Yang, Yoon Kim, Kewei Tu


Abstract
Scaling dense PCFGs to thousands of nonterminals via low-rank parameterizations of the rule probability tensor has been shown to be beneficial for unsupervised parsing. However, PCFGs scaled this way still perform poorly as a language model, and even underperform similarly-sized HMMs. This work introduces SimplePCFG, a simple PCFG formalism with independent left and right productions. Despite imposing a stronger independence assumption than the low-rank approach, we find that this formalism scales more effectively both as a language model and as an unsupervised parser. We further introduce FlashInside, a hardware IO-aware implementation of the inside algorithm for efficiently scaling simple PCFGs. Through extensive experiments on multiple grammar induction benchmarks, we validate the effectiveness of simple PCFGs over low-rank baselines.
Anthology ID:
2023.findings-emnlp.113
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1662–1669
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.113
DOI:
10.18653/v1/2023.findings-emnlp.113
Bibkey:
Cite (ACL):
Wei Liu, Songlin Yang, Yoon Kim, and Kewei Tu. 2023. Simple Hardware-Efficient PCFGs with Independent Left and Right Productions. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1662–1669, Singapore. Association for Computational Linguistics.
Cite (Informal):
Simple Hardware-Efficient PCFGs with Independent Left and Right Productions (Liu et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2023.findings-emnlp.113.pdf