Incorporating Temporal Information in Entailment Graph Mining

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.
Original languageEnglish
Title of host publicationProceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)
PublisherAssociation for Computational Linguistics
Number of pages12
ISBN (Print)978-1-952148-42-2
Publication statusPublished - 13 Dec 2020
Event14th Workshop on Graph-Based Natural Language Processing - Online workshop
Duration: 13 Dec 202013 Dec 2020


Workshop14th Workshop on Graph-Based Natural Language Processing
Abbreviated titleTextGraphs 20202
CityOnline workshop
Internet address

Fingerprint Dive into the research topics of 'Incorporating Temporal Information in Entailment Graph Mining'. Together they form a unique fingerprint.

Cite this