Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference

Lasha Abzianidze


Abstract
Tackling Natural Language Inference with a logic-based method is becoming less and less common. While this might have been counterintuitive several decades ago, nowadays it seems pretty obvious. The main reasons for such a conception are that (a) logic-based methods are usually brittle when it comes to processing wide-coverage texts, and (b) instead of automatically learning from data, they require much of manual effort for development. We make a step towards to overcome such shortcomings by modeling learning from data as abduction: reversing a theorem-proving procedure to abduce semantic relations that serve as the best explanation for the gold label of an inference problem. In other words, instead of proving sentence-level inference relations with the help of lexical relations, the lexical relations are proved taking into account the sentence-level inference relations. We implement the learning method in a tableau theorem prover for natural language and show that it improves the performance of the theorem prover on the SICK dataset by 1.4% while still maintaining high precision (>94%). The obtained results are competitive with the state of the art among logic-based systems.
Anthology ID:
2020.starsem-1.3
Volume:
Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Iryna Gurevych, Marianna Apidianaki, Manaal Faruqui
Venue:
*SEM
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
20–31
Language:
URL:
https://aclanthology.org/2020.starsem-1.3
DOI:
Bibkey:
Cite (ACL):
Lasha Abzianidze. 2020. Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference. In Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics, pages 20–31, Barcelona, Spain (Online). Association for Computational Linguistics.
Cite (Informal):
Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference (Abzianidze, *SEM 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.starsem-1.3.pdf
Code
 kovvalsky/LangPro
Data
SICK