Tensors over Semirings for Latent-Variable Weighted Logic Programs

Esma Balkir, Daniel Gildea, Shay B. Cohen


Abstract
Semiring parsing is an elegant framework for describing parsers by using semiring weighted logic programs. In this paper we present a generalization of this concept: latent-variable semiring parsing. With our framework, any semiring weighted logic program can be latentified by transforming weights from scalar values of a semiring to rank-n arrays, or tensors, of semiring values, allowing the modelling of latent-variable models within the semiring parsing framework. Semiring is too strong a notion when dealing with tensors, and we have to resort to a weaker structure: a partial semiring. We prove that this generalization preserves all the desired properties of the original semiring framework while strictly increasing its expressiveness.
Anthology ID:
2020.iwpt-1.8
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
Venues:
ACL | IWPT | WS
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
73–90
Language:
URL:
https://aclanthology.org/2020.iwpt-1.8
DOI:
10.18653/v1/2020.iwpt-1.8
Bibkey:
Cite (ACL):
Esma Balkir, Daniel Gildea, and Shay B. Cohen. 2020. Tensors over Semirings for Latent-Variable Weighted Logic Programs. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages 73–90, Online. Association for Computational Linguistics.
Cite (Informal):
Tensors over Semirings for Latent-Variable Weighted Logic Programs (Balkir et al., IWPT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.iwpt-1.8.pdf
Dataset:
 2020.iwpt-1.8.Dataset.pdf
Video:
 http://slideslive.com/38929675