Multivalent Entailment Graphs for Question Answering

Nick McKenna, Liane Guillou, Mohammad Javad Hosseini, Sander Bijl de Vroe, Mark Johnson, Mark Steedman


Abstract
Drawing inferences between open-domain natural language predicates is a necessity for true language understanding. There has been much progress in unsupervised learning of entailment graphs for this purpose. We make three contributions: (1) we reinterpret the Distributional Inclusion Hypothesis to model entailment between predicates of different valencies, like DEFEAT(Biden, Trump) entails WIN(Biden); (2) we actualize this theory by learning unsupervised Multivalent Entailment Graphs of open-domain predicates; and (3) we demonstrate the capabilities of these graphs on a novel question answering task. We show that directional entailment is more helpful for inference than non-directional similarity on questions of fine-grained semantics. We also show that drawing on evidence across valencies answers more questions than by using only the same valency evidence.
Anthology ID:
2021.emnlp-main.840
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10758–10768
Language:
URL:
https://aclanthology.org/2021.emnlp-main.840
DOI:
10.18653/v1/2021.emnlp-main.840
Bibkey:
Cite (ACL):
Nick McKenna, Liane Guillou, Mohammad Javad Hosseini, Sander Bijl de Vroe, Mark Johnson, and Mark Steedman. 2021. Multivalent Entailment Graphs for Question Answering. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10758–10768, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Multivalent Entailment Graphs for Question Answering (McKenna et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.840.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.840.mp4