Abstract
Hidden Markov Models (HMMs) and Probabilistic Context-Free Grammars (PCFGs) are widely used structured models, both of which can be represented as factor graph grammars (FGGs), a powerful formalism capable of describing a wide range of models. Recent research found it beneficial to use large state spaces for HMMs and PCFGs. However, inference with large state spaces is computationally demanding, especially for PCFGs. To tackle this challenge, we leverage tensor rank decomposition (aka. CPD) to decrease inference computational complexities for a subset of FGGs subsuming HMMs and PCFGs. We apply CPD on the factors of an FGG and then construct a new FGG defined in the rank space. Inference with the new FGG produces the same result but has a lower time complexity when the rank size is smaller than the state size. We conduct experiments on HMM language modeling and unsupervised PCFG parsing, showing better performance than previous work. Our code is publicly available at https://github.com/VPeterV/RankSpace-Models.- Anthology ID:
- 2022.naacl-main.353
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4797–4809
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.353
- DOI:
- 10.18653/v1/2022.naacl-main.353
- Cite (ACL):
- Songlin Yang, Wei Liu, and Kewei Tu. 2022. Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4797–4809, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs (Yang et al., NAACL 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.naacl-main.353.pdf
- Code
- sustcsonglin/TN-PCFG + additional community code
- Data
- PTB Diagnostic ECG Database