Incorporating Temporal Information in Entailment Graph Mining

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


Abstract
We present a novel method for injecting temporality into entailment graphs to address the problem of spurious entailments, which may arise from similar but temporally distinct events involving the same pair of entities. We focus on the sports domain in which the same pairs of teams play on different occasions, with different outcomes. We present an unsupervised model that aims to learn entailments such as win/lose → play, while avoiding the pitfall of learning non-entailments such as win ̸→ lose. We evaluate our model on a manually constructed dataset, showing that incorporating time intervals and applying a temporal window around them, are effective strategies.
Anthology ID:
2020.textgraphs-1.7
Volume:
Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
TextGraphs
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
60–71
Language:
URL:
https://aclanthology.org/2020.textgraphs-1.7
DOI:
10.18653/v1/2020.textgraphs-1.7
Bibkey:
Cite (ACL):
Liane Guillou, Sander Bijl de Vroe, Mohammad Javad Hosseini, Mark Johnson, and Mark Steedman. 2020. Incorporating Temporal Information in Entailment Graph Mining. In Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs), pages 60–71, Barcelona, Spain (Online). Association for Computational Linguistics.
Cite (Informal):
Incorporating Temporal Information in Entailment Graph Mining (Guillou et al., TextGraphs 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.textgraphs-1.7.pdf
Code
 lianeg/temporal-entailment-sports-dataset
Data
FIGER