Bridging knowledge gaps in neural entailment via symbolic models

Dongyeop Kang; Tushar Khot; Ashish Sabharwal; Peter Clark

Bridging knowledge gaps in neural entailment via symbolic models

Dongyeop Kang
, Tushar Khot
, Ashish Sabharwal
, Peter Clark

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

Abstract

Most textual entailment models focus on lexical gaps between the premise text and the hypothesis, but rarely on knowledge gaps. We focus on filling these knowledge gaps in the Science Entailment task, by leveraging an external structured knowledge base (KB) of science facts. Our new architecture combines standard neural entailment models with a knowledge lookup module. To facilitate this lookup, we propose a fact-level decomposition of the hypothesis, and verifying the resulting sub-facts against both the textual premise and the structured KB. Our model, NSnet, learns to aggregate predictions from these heterogeneous data formats. On the SciTail dataset, NSnet outperforms a simpler combination of the two predictions by 3% and the base entailment model by 5%.

Original language	English (US)
Title of host publication	Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Editors	Ellen Riloff, David Chiang, Julia Hockenmaier, Jun'ichi Tsujii
Publisher	Association for Computational Linguistics
Pages	4940-4945
Number of pages	6
ISBN (Electronic)	9781948087841
State	Published - 2020
Externally published	Yes
Event	2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 - Brussels, Belgium Duration: Oct 31 2018 → Nov 4 2018

Publication series

Name	Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

Conference

Conference	2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Country/Territory	Belgium
City	Brussels
Period	10/31/18 → 11/4/18

Bibliographical note

Publisher Copyright:
© 2018 Association for Computational Linguistics

Find It

Find It at U of M Libraries

Cite this

Kang, D., Khot, T., Sabharwal, A., & Clark, P. (2020). Bridging knowledge gaps in neural entailment via symbolic models. In E. Riloff, D. Chiang, J. Hockenmaier, & J. Tsujii (Eds.), Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 (pp. 4940-4945). (Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018). Association for Computational Linguistics.

Bridging knowledge gaps in neural entailment via symbolic models. / Kang, Dongyeop; Khot, Tushar; Sabharwal, Ashish et al.
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018. ed. / Ellen Riloff; David Chiang; Julia Hockenmaier; Jun'ichi Tsujii. Association for Computational Linguistics, 2020. p. 4940-4945 (Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018).

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

Kang, D, Khot, T, Sabharwal, A & Clark, P 2020, Bridging knowledge gaps in neural entailment via symbolic models. in E Riloff, D Chiang, J Hockenmaier & J Tsujii (eds), Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018, Association for Computational Linguistics, pp. 4940-4945, 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018, Brussels, Belgium, 10/31/18.

Kang D, Khot T, Sabharwal A, Clark P. Bridging knowledge gaps in neural entailment via symbolic models. In Riloff E, Chiang D, Hockenmaier J, Tsujii J, editors, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018. Association for Computational Linguistics. 2020. p. 4940-4945. (Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018).

Kang, Dongyeop ; Khot, Tushar ; Sabharwal, Ashish et al. / Bridging knowledge gaps in neural entailment via symbolic models. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018. editor / Ellen Riloff ; David Chiang ; Julia Hockenmaier ; Jun'ichi Tsujii. Association for Computational Linguistics, 2020. pp. 4940-4945 (Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018).

@inproceedings{18401a8d9e3847cfb4e91f4e19026dde,

title = "Bridging knowledge gaps in neural entailment via symbolic models",

abstract = "Most textual entailment models focus on lexical gaps between the premise text and the hypothesis, but rarely on knowledge gaps. We focus on filling these knowledge gaps in the Science Entailment task, by leveraging an external structured knowledge base (KB) of science facts. Our new architecture combines standard neural entailment models with a knowledge lookup module. To facilitate this lookup, we propose a fact-level decomposition of the hypothesis, and verifying the resulting sub-facts against both the textual premise and the structured KB. Our model, NSnet, learns to aggregate predictions from these heterogeneous data formats. On the SciTail dataset, NSnet outperforms a simpler combination of the two predictions by 3\% and the base entailment model by 5\%.",

author = "Dongyeop Kang and Tushar Khot and Ashish Sabharwal and Peter Clark",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics; 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 ; Conference date: 31-10-2018 Through 04-11-2018",

year = "2020",

language = "English (US)",

series = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",

publisher = "Association for Computational Linguistics",

pages = "4940--4945",

editor = "Ellen Riloff and David Chiang and Julia Hockenmaier and Jun'ichi Tsujii",

booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",

}

TY - GEN

T1 - Bridging knowledge gaps in neural entailment via symbolic models

AU - Kang, Dongyeop

AU - Khot, Tushar

AU - Sabharwal, Ashish

AU - Clark, Peter

PY - 2020

Y1 - 2020

N2 - Most textual entailment models focus on lexical gaps between the premise text and the hypothesis, but rarely on knowledge gaps. We focus on filling these knowledge gaps in the Science Entailment task, by leveraging an external structured knowledge base (KB) of science facts. Our new architecture combines standard neural entailment models with a knowledge lookup module. To facilitate this lookup, we propose a fact-level decomposition of the hypothesis, and verifying the resulting sub-facts against both the textual premise and the structured KB. Our model, NSnet, learns to aggregate predictions from these heterogeneous data formats. On the SciTail dataset, NSnet outperforms a simpler combination of the two predictions by 3% and the base entailment model by 5%.

AB - Most textual entailment models focus on lexical gaps between the premise text and the hypothesis, but rarely on knowledge gaps. We focus on filling these knowledge gaps in the Science Entailment task, by leveraging an external structured knowledge base (KB) of science facts. Our new architecture combines standard neural entailment models with a knowledge lookup module. To facilitate this lookup, we propose a fact-level decomposition of the hypothesis, and verifying the resulting sub-facts against both the textual premise and the structured KB. Our model, NSnet, learns to aggregate predictions from these heterogeneous data formats. On the SciTail dataset, NSnet outperforms a simpler combination of the two predictions by 3% and the base entailment model by 5%.

UR - https://www.scopus.com/pages/publications/85081714717

UR - https://www.scopus.com/pages/publications/85081714717#tab=citedBy

M3 - Conference contribution

AN - SCOPUS:85081714717

T3 - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

SP - 4940

EP - 4945

BT - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

A2 - Riloff, Ellen

A2 - Chiang, David

A2 - Hockenmaier, Julia

A2 - Tsujii, Jun'ichi

PB - Association for Computational Linguistics

T2 - 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

Y2 - 31 October 2018 through 4 November 2018

ER -

Bridging knowledge gaps in neural entailment via symbolic models

Abstract

Publication series

Conference

Bibliographical note

Find It

Other files and links

Fingerprint

Cite this