I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning

Jungwoo Lim; Dongsuk Oh; Yoonna Jang; Kisu Yang; Heuiseok Lim

I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning

Jungwoo Lim, Dongsuk Oh, Yoonna Jang, Kisu Yang, Heuiseok Lim

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

Abstract

CommonsenseQA is a task in which a correct answer is predicted through commonsense reasoning with pre-defined knowledge. Most previous works have aimed to improve the performance with distributed representation without considering the process of predicting the answer from the semantic representation of the question. To shed light upon the semantic interpretation of the question, we propose an AMR-ConceptNet-Pruned (ACP) graph. The ACP graph is pruned from a full integrated graph encompassing Abstract Meaning Representation (AMR) graph generated from input questions and an external commonsense knowledge graph, ConceptNet (CN). Then the ACP graph is exploited to interpret the reasoning path as well as to predict the correct answer on the CommonsenseQA task. This paper presents the manner in which the commonsense reasoning process can be interpreted with the relations and concepts provided by the ACP graph. Moreover, ACP-based models are shown to outperform the baselines.

Original language	English
Title of host publication	COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference
Editors	Donia Scott, Nuria Bel, Chengqing Zong
Publisher	Association for Computational Linguistics (ACL)
Pages	2459-2471
Number of pages	13
ISBN (Electronic)	9781952148279
Publication status	Published - 2020
Event	28th International Conference on Computational Linguistics, COLING 2020 - Virtual, Online, Spain Duration: 2020 Dec 8 → 2020 Dec 13

Publication series

Name	COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference

Conference

Conference	28th International Conference on Computational Linguistics, COLING 2020
Country/Territory	Spain
City	Virtual, Online
Period	20/12/8 → 20/12/13

Bibliographical note

Funding Information:
This work was supported by Institute for Information & communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT) (No. 2020-0-00368, A Neural-Symbolic Model for Knowledge Acquisition and Inference Techniques). Also, this research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2020-2018-0-01405) supervised by the IITP(Institute for Information & Communications Technology Planning & Evaluation)

Publisher Copyright:
© 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

ASJC Scopus subject areas

Computer Science Applications
Computational Theory and Mathematics
Theoretical Computer Science

Cite this

Lim, J., Oh, D., Jang, Y., Yang, K., & Lim, H. (2020). I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning. In D. Scott, N. Bel, & C. Zong (Eds.), COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference (pp. 2459-2471). (COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference). Association for Computational Linguistics (ACL).

I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning. / Lim, Jungwoo; Oh, Dongsuk; Jang, Yoonna et al.
COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. ed. / Donia Scott; Nuria Bel; Chengqing Zong. Association for Computational Linguistics (ACL), 2020. p. 2459-2471 (COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference).

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

Lim, J, Oh, D, Jang, Y, Yang, K & Lim, H 2020, I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning. in D Scott, N Bel & C Zong (eds), COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 2459-2471, 28th International Conference on Computational Linguistics, COLING 2020, Virtual, Online, Spain, 20/12/8.

Lim J, Oh D, Jang Y, Yang K, Lim H. I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning. In Scott D, Bel N, Zong C, editors, COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2020. p. 2459-2471. (COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference).

Lim, Jungwoo ; Oh, Dongsuk ; Jang, Yoonna et al. / I Know What You Asked : Graph Path Learning using AMR for Commonsense Reasoning. COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. editor / Donia Scott ; Nuria Bel ; Chengqing Zong. Association for Computational Linguistics (ACL), 2020. pp. 2459-2471 (COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference).

@inproceedings{ba018588b34045469c39373f0deaab54,

title = "I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning",

abstract = "CommonsenseQA is a task in which a correct answer is predicted through commonsense reasoning with pre-defined knowledge. Most previous works have aimed to improve the performance with distributed representation without considering the process of predicting the answer from the semantic representation of the question. To shed light upon the semantic interpretation of the question, we propose an AMR-ConceptNet-Pruned (ACP) graph. The ACP graph is pruned from a full integrated graph encompassing Abstract Meaning Representation (AMR) graph generated from input questions and an external commonsense knowledge graph, ConceptNet (CN). Then the ACP graph is exploited to interpret the reasoning path as well as to predict the correct answer on the CommonsenseQA task. This paper presents the manner in which the commonsense reasoning process can be interpreted with the relations and concepts provided by the ACP graph. Moreover, ACP-based models are shown to outperform the baselines.",

author = "Jungwoo Lim and Dongsuk Oh and Yoonna Jang and Kisu Yang and Heuiseok Lim",

note = "Funding Information: This work was supported by Institute for Information & communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT) (No. 2020-0-00368, A Neural-Symbolic Model for Knowledge Acquisition and Inference Techniques). Also, this research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2020-2018-0-01405) supervised by the IITP(Institute for Information & Communications Technology Planning & Evaluation) Publisher Copyright: {\textcopyright} 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.; 28th International Conference on Computational Linguistics, COLING 2020 ; Conference date: 08-12-2020 Through 13-12-2020",

year = "2020",

language = "English",

series = "COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference",

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

pages = "2459--2471",

editor = "Donia Scott and Nuria Bel and Chengqing Zong",

booktitle = "COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference",

}

TY - GEN

T1 - I Know What You Asked

T2 - 28th International Conference on Computational Linguistics, COLING 2020

AU - Lim, Jungwoo

AU - Oh, Dongsuk

AU - Jang, Yoonna

AU - Yang, Kisu

AU - Lim, Heuiseok

N1 - Funding Information: This work was supported by Institute for Information & communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT) (No. 2020-0-00368, A Neural-Symbolic Model for Knowledge Acquisition and Inference Techniques). Also, this research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2020-2018-0-01405) supervised by the IITP(Institute for Information & Communications Technology Planning & Evaluation) Publisher Copyright: © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

PY - 2020

Y1 - 2020

N2 - CommonsenseQA is a task in which a correct answer is predicted through commonsense reasoning with pre-defined knowledge. Most previous works have aimed to improve the performance with distributed representation without considering the process of predicting the answer from the semantic representation of the question. To shed light upon the semantic interpretation of the question, we propose an AMR-ConceptNet-Pruned (ACP) graph. The ACP graph is pruned from a full integrated graph encompassing Abstract Meaning Representation (AMR) graph generated from input questions and an external commonsense knowledge graph, ConceptNet (CN). Then the ACP graph is exploited to interpret the reasoning path as well as to predict the correct answer on the CommonsenseQA task. This paper presents the manner in which the commonsense reasoning process can be interpreted with the relations and concepts provided by the ACP graph. Moreover, ACP-based models are shown to outperform the baselines.

AB - CommonsenseQA is a task in which a correct answer is predicted through commonsense reasoning with pre-defined knowledge. Most previous works have aimed to improve the performance with distributed representation without considering the process of predicting the answer from the semantic representation of the question. To shed light upon the semantic interpretation of the question, we propose an AMR-ConceptNet-Pruned (ACP) graph. The ACP graph is pruned from a full integrated graph encompassing Abstract Meaning Representation (AMR) graph generated from input questions and an external commonsense knowledge graph, ConceptNet (CN). Then the ACP graph is exploited to interpret the reasoning path as well as to predict the correct answer on the CommonsenseQA task. This paper presents the manner in which the commonsense reasoning process can be interpreted with the relations and concepts provided by the ACP graph. Moreover, ACP-based models are shown to outperform the baselines.

UR - http://www.scopus.com/inward/record.url?scp=85118300409&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85118300409

T3 - COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference

SP - 2459

EP - 2471

BT - COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference

A2 - Scott, Donia

A2 - Bel, Nuria

A2 - Zong, Chengqing

PB - Association for Computational Linguistics (ACL)

Y2 - 8 December 2020 through 13 December 2020

ER -

I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this