Blindness to Modality Helps Entailment Graph Mining

Liane Guillou; Sander Bijl de Vroe; Mark Johnson; Mark Steedman

Blindness to Modality Helps Entailment Graph Mining

Liane Guillou, Sander Bijl de Vroe, Mark Johnson, Mark Steedman

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

Abstract / Description of output

Understanding linguistic modality is widely seen as important for downstream tasks such as Question Answering and Knowledge Graph Population. Entailment Graph learning might also be expected to benefit from attention to modality. We build Entailment Graphs using a news corpus filtered with a modality parser, and show that stripping modal modifiers from predicates in fact increases performance. This suggests that for some tasks, the pragmatics of modal modification of predicates allows them to contribute as evidence of entailment.

Original language	English
Title of host publication	Proceedings of the Second Workshop on Insights from Negative Results in NLP
Editors	João Sedoc, Anna Rogers, Anna Rumshisky, Shabnam Tafreshi
Place of Publication	Stroudsburg, PA, United States
Publisher	Association for Computational Linguistics (ACL)
Pages	110-116
Number of pages	7
ISBN (Electronic)	978-1-954085-93-0
Publication status	Published - 10 Nov 2021
Event	Workshop on Insights from Negative Results in NLP - Punta Cana, Dominican Republic Duration: 10 Nov 2021 → 10 Nov 2021 https://insights-workshop.github.io/2021/

Workshop

Workshop	Workshop on Insights from Negative Results in NLP
Country/Territory	Dominican Republic
City	Punta Cana
Period	10/11/21 → 10/11/21
Internet address	https://insights-workshop.github.io/2021/

Access to Document

Blindness_GUILLOU_DOA05092021_VOR_CC-BYFinal published version, 291 KBLicence: Creative Commons: Attribution (CC-BY)

https://aclanthology.org/2021.insights-1.16/Licence: 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{f39853ac680e4320b11c9972ac4eff86,

title = "Blindness to Modality Helps Entailment Graph Mining",

abstract = "Understanding linguistic modality is widely seen as important for downstream tasks such as Question Answering and Knowledge Graph Population. Entailment Graph learning might also be expected to benefit from attention to modality. We build Entailment Graphs using a news corpus filtered with a modality parser, and show that stripping modal modifiers from predicates in fact increases performance. This suggests that for some tasks, the pragmatics of modal modification of predicates allows them to contribute as evidence of entailment.",

author = "Liane Guillou and {Bijl de Vroe}, Sander and Mark Johnson and Mark Steedman",

year = "2021",

month = nov,

day = "10",

language = "English",

pages = "110--116",

editor = "Jo{\~a}o Sedoc and Anna Rogers and Anna Rumshisky and Shabnam Tafreshi",

booktitle = "Proceedings of the Second Workshop on Insights from Negative Results in NLP",

publisher = "Association for Computational Linguistics (ACL)",

note = "Workshop on Insights from Negative Results in NLP ; Conference date: 10-11-2021 Through 10-11-2021",

url = "https://insights-workshop.github.io/2021/",

}

Guillou, L, Bijl de Vroe, S, Johnson, M & Steedman, M 2021, Blindness to Modality Helps Entailment Graph Mining. in J Sedoc, A Rogers, A Rumshisky & S Tafreshi (eds), Proceedings of the Second Workshop on Insights from Negative Results in NLP. Association for Computational Linguistics (ACL), Stroudsburg, PA, United States, pp. 110-116, Workshop on Insights from Negative Results in NLP, Punta Cana, Dominican Republic, 10/11/21. <https://aclanthology.org/2021.insights-1.16/>

Blindness to Modality Helps Entailment Graph Mining. / Guillou, Liane; Bijl de Vroe, Sander; Johnson, Mark et al.
Proceedings of the Second Workshop on Insights from Negative Results in NLP. ed. / João Sedoc; Anna Rogers; Anna Rumshisky; Shabnam Tafreshi. Stroudsburg, PA, United States: Association for Computational Linguistics (ACL), 2021. p. 110-116.

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

TY - GEN

T1 - Blindness to Modality Helps Entailment Graph Mining

AU - Guillou, Liane

AU - Bijl de Vroe, Sander

AU - Johnson, Mark

AU - Steedman, Mark

PY - 2021/11/10

Y1 - 2021/11/10

N2 - Understanding linguistic modality is widely seen as important for downstream tasks such as Question Answering and Knowledge Graph Population. Entailment Graph learning might also be expected to benefit from attention to modality. We build Entailment Graphs using a news corpus filtered with a modality parser, and show that stripping modal modifiers from predicates in fact increases performance. This suggests that for some tasks, the pragmatics of modal modification of predicates allows them to contribute as evidence of entailment.

AB - Understanding linguistic modality is widely seen as important for downstream tasks such as Question Answering and Knowledge Graph Population. Entailment Graph learning might also be expected to benefit from attention to modality. We build Entailment Graphs using a news corpus filtered with a modality parser, and show that stripping modal modifiers from predicates in fact increases performance. This suggests that for some tasks, the pragmatics of modal modification of predicates allows them to contribute as evidence of entailment.

M3 - Conference contribution

SP - 110

EP - 116

BT - Proceedings of the Second Workshop on Insights from Negative Results in NLP

A2 - Sedoc, João

A2 - Rogers, Anna

A2 - Rumshisky, Anna

A2 - Tafreshi, Shabnam

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg, PA, United States

T2 - Workshop on Insights from Negative Results in NLP

Y2 - 10 November 2021 through 10 November 2021

ER -

Blindness to Modality Helps Entailment Graph Mining

Abstract / Description of output

Workshop

Access to Document

Fingerprint

Projects

SEMANTAX-Form-Independent Semantics for Natural Language Understanding

Cite this