Incorporating Temporal Information in Entailment Graph Mining

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

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 proceeding › Conference contribution

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.

Original language	English
Title of host publication	Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)
Place of Publication	Barcelona, Spain
Publisher	Association for Computational Linguistics
Pages	60-71
Number of pages	12
ISBN (Print)	978-1-952148-42-2
Publication status	Published - 13 Dec 2020
Event	14th Workshop on Graph-Based Natural Language Processing - Online workshop Duration: 13 Dec 2020 → 13 Dec 2020 https://sites.google.com/view/textgraphs2020

Workshop

Workshop	14th Workshop on Graph-Based Natural Language Processing
Abbreviated title	TextGraphs 20202
City	Online workshop
Period	13/12/20 → 13/12/20
Internet address	https://sites.google.com/view/textgraphs2020

Access to Document

Incorporating Temporal_GUILLOU_DOA25102020_AFVAccepted author manuscript, 310 KBLicence: Creative Commons: Attribution (CC-BY)
Incorporating Temporal_GUILLOU_DOA25102020Final published version, 369 KBLicence: Creative Commons: Attribution (CC-BY)

https://www.aclweb.org/anthology/2020.textgraphs-1.7Licence: Creative Commons: Attribution (CC-BY)

SEMANTAX-Form-Independent Semantics for Natural Language Understanding
Steedman, M.
EU government bodies
1/08/17 → 31/07/23
Project: Research

File

Cite this

@inproceedings{5aa8efef20064782ac3c477951a5a16e,

title = "Incorporating Temporal Information in Entailment Graph Mining",

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.",

author = "Liane Guillou and {Bijl De Vroe}, Sander and Hosseini, {Mohammad Javad} and Mark Johnson and Mark Steedman",

year = "2020",

month = dec,

day = "13",

language = "English",

isbn = "978-1-952148-42-2",

pages = "60--71",

booktitle = "Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)",

publisher = "Association for Computational Linguistics",

note = "14th Workshop on Graph-Based Natural Language Processing, TextGraphs 20202 ; Conference date: 13-12-2020 Through 13-12-2020",

url = "https://sites.google.com/view/textgraphs2020",

}

Guillou, L, Bijl De Vroe, S, Hosseini, MJ, Johnson, M & Steedman, M 2020, Incorporating Temporal Information in Entailment Graph Mining. in Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs). Association for Computational Linguistics, Barcelona, Spain, pp. 60-71, 14th Workshop on Graph-Based Natural Language Processing, Online workshop, 13/12/20. <https://www.aclweb.org/anthology/2020.textgraphs-1.7>

Incorporating Temporal Information in Entailment Graph Mining. / Guillou, Liane; Bijl De Vroe, Sander; Hosseini, Mohammad Javad et al.
Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs). Barcelona, Spain: Association for Computational Linguistics, 2020. p. 60-71.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Incorporating Temporal Information in Entailment Graph Mining

AU - Guillou, Liane

AU - Bijl De Vroe, Sander

AU - Hosseini, Mohammad Javad

AU - Johnson, Mark

AU - Steedman, Mark

PY - 2020/12/13

Y1 - 2020/12/13

N2 - 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.

AB - 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.

M3 - Conference contribution

SN - 978-1-952148-42-2

SP - 60

EP - 71

BT - Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)

PB - Association for Computational Linguistics

CY - Barcelona, Spain

T2 - 14th Workshop on Graph-Based Natural Language Processing

Y2 - 13 December 2020 through 13 December 2020

ER -

Incorporating Temporal Information in Entailment Graph Mining

Abstract

Workshop

Access to Document

Fingerprint

Projects

SEMANTAX-Form-Independent Semantics for Natural Language Understanding

Cite this