Toward Diverse Precondition Generation

Heeyoung Kwon, Nathanael Chambers, Niranjan Balasubramanian


Abstract
A typical goal for language understanding is to logically connect the events of a discourse, but often connective events are not described due to their commonsense nature. In order to address this deficit, we focus here on generating precondition events. Precondition generation can be framed as a sequence-to-sequence problem: given a target event, generate a possible precondition. However, in most real-world scenarios, an event can have several preconditions, which is not always suitable for standard seq2seq frameworks. We propose DiP, the Diverse Precondition generation system that can generate unique and diverse preconditions. DiP consists of three stages of the generative process – an event sampler, a candidate generator, and a post-processor. The event sampler provides control codes (precondition triggers) which the candidate generator uses to focus its generation. Post-processing further improves the results through re-ranking and filtering. Unlike other conditional generation systems, DiP automatically generates control codes without training on diverse examples. Analysis reveals that DiP improves the diversity of preconditions significantly compared to a beam search baseline. Also, manual evaluation shows that DiP generates more preconditions than a strong nucleus sampling baseline.
Anthology ID:
2021.starsem-1.15
Volume:
Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics
Month:
August
Year:
2021
Address:
Online
Editors:
Lun-Wei Ku, Vivi Nastase, Ivan Vulić
Venue:
*SEM
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
160–172
Language:
URL:
https://aclanthology.org/2021.starsem-1.15
DOI:
10.18653/v1/2021.starsem-1.15
Bibkey:
Cite (ACL):
Heeyoung Kwon, Nathanael Chambers, and Niranjan Balasubramanian. 2021. Toward Diverse Precondition Generation. In Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics, pages 160–172, Online. Association for Computational Linguistics.
Cite (Informal):
Toward Diverse Precondition Generation (Kwon et al., *SEM 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.starsem-1.15.pdf