Consistent Bidirectional Language Modelling: Expressive Power and Representational Conciseness

Georgi Shopov, Stefan Gerdjikov


Abstract
The inability to utilise future contexts and the pre-determined left-to-right generation order are major limitations of unidirectional language models. Bidirectionality has been introduced to address those deficiencies. However, a crucial shortcoming of bidirectional language models is the potential inconsistency of their conditional distributions. This fundamental flaw greatly diminishes their applicability and hinders their capability of tractable sampling and likelihood computation. In this work, we introduce a class of bidirectional language models, called latent language models, that are consistent by definition and can be efficiently used both for generation and scoring of sequences. We define latent language models based on the well-understood formalism of bisequential decompositions from automata theory. This formal correspondence allows us to precisely charaterise the abilities and limitations of a subclass of latent language models, called rational language models. As a result, we obtain that latent language models are exponentially more concise and significantly more expressive than unidirectional language models.
Anthology ID:
2024.emnlp-main.328
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5724–5768
Language:
URL:
https://aclanthology.org/2024.emnlp-main.328
DOI:
Bibkey:
Cite (ACL):
Georgi Shopov and Stefan Gerdjikov. 2024. Consistent Bidirectional Language Modelling: Expressive Power and Representational Conciseness. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 5724–5768, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Consistent Bidirectional Language Modelling: Expressive Power and Representational Conciseness (Shopov & Gerdjikov, EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.328.pdf