ECNU at SemEval-2018 Task 12: An End-to-End Attention-based Neural Network for the Argument Reasoning Comprehension Task

Junfeng Tian; Man Lan; Yuanbin Wu

doi:10.18653/v1/s18-1184

ECNU at SemEval-2018 Task 12: An End-to-End Attention-based Neural Network for the Argument Reasoning Comprehension Task

Junfeng Tian
, Man Lan^*
, Yuanbin Wu

^*Corresponding author for this work

School of Computer Science and Technology

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

4 Scopus citations

Abstract

This paper presents our submissions to SemEval 2018 Task 12: the Argument Reasoning Comprehension Task. We investigate an end-to-end attention-based neural network to represent the two lexically close candidate warrants. On the one hand, we extract their different parts as attention vectors to obtain distinguishable representations. On the other hand, we use their surrounds (i.e., claim, reason, debate context) as another attention vectors to get contextual representations, which work as final clues to select the correct warrant. Our model achieves 60.4% accuracy and ranks 3^rd among 22 participating systems.

Original language	English
Title of host publication	NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop
Editors	Marianna Apidianaki, Marianna Apidianaki, Saif M. Mohammad, Jonathan May, Ekaterina Shutova, Steven Bethard, Marine Carpuat
Publisher	Association for Computational Linguistics (ACL)
Pages	1094-1098
Number of pages	5
ISBN (Electronic)	9781948087209
DOIs	https://doi.org/10.18653/v1/s18-1184
State	Published - 2018
Event	12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 - New Orleans, United States Duration: 5 Jun 2018 → 6 Jun 2018

Publication series

Name	NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop

Conference

Conference	12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018
Country/Territory	United States
City	New Orleans
Period	5/06/18 → 6/06/18

Access to Document

10.18653/v1/s18-1184

Cite this

Tian, J., Lan, M., & Wu, Y. (2018). ECNU at SemEval-2018 Task 12: An End-to-End Attention-based Neural Network for the Argument Reasoning Comprehension Task. In M. Apidianaki, M. Apidianaki, S. M. Mohammad, J. May, E. Shutova, S. Bethard, & M. Carpuat (Eds.), NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop (pp. 1094-1098). (NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/s18-1184

Tian, Junfeng ; Lan, Man ; Wu, Yuanbin. / ECNU at SemEval-2018 Task 12 : An End-to-End Attention-based Neural Network for the Argument Reasoning Comprehension Task. NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop. editor / Marianna Apidianaki ; Marianna Apidianaki ; Saif M. Mohammad ; Jonathan May ; Ekaterina Shutova ; Steven Bethard ; Marine Carpuat. Association for Computational Linguistics (ACL), 2018. pp. 1094-1098 (NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop).

@inproceedings{54c26a2c63f240a19b4ecac0ec897953,

title = "ECNU at SemEval-2018 Task 12: An End-to-End Attention-based Neural Network for the Argument Reasoning Comprehension Task",

abstract = "This paper presents our submissions to SemEval 2018 Task 12: the Argument Reasoning Comprehension Task. We investigate an end-to-end attention-based neural network to represent the two lexically close candidate warrants. On the one hand, we extract their different parts as attention vectors to obtain distinguishable representations. On the other hand, we use their surrounds (i.e., claim, reason, debate context) as another attention vectors to get contextual representations, which work as final clues to select the correct warrant. Our model achieves 60.4\% accuracy and ranks 3rd among 22 participating systems.",

author = "Junfeng Tian and Man Lan and Yuanbin Wu",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics; 12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 ; Conference date: 05-06-2018 Through 06-06-2018",

year = "2018",

doi = "10.18653/v1/s18-1184",

language = "英语",

series = "NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop",

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

pages = "1094--1098",

editor = "Marianna Apidianaki and Marianna Apidianaki and Mohammad, \{Saif M.\} and Jonathan May and Ekaterina Shutova and Steven Bethard and Marine Carpuat",

booktitle = "NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop",

address = "澳大利亚",

}

Tian, J, Lan, M & Wu, Y 2018, ECNU at SemEval-2018 Task 12: An End-to-End Attention-based Neural Network for the Argument Reasoning Comprehension Task. in M Apidianaki, M Apidianaki, SM Mohammad, J May, E Shutova, S Bethard & M Carpuat (eds), NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop. NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop, Association for Computational Linguistics (ACL), pp. 1094-1098, 12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018, New Orleans, United States, 5/06/18. https://doi.org/10.18653/v1/s18-1184

ECNU at SemEval-2018 Task 12: An End-to-End Attention-based Neural Network for the Argument Reasoning Comprehension Task. / Tian, Junfeng; Lan, Man; Wu, Yuanbin.
NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop. ed. / Marianna Apidianaki; Marianna Apidianaki; Saif M. Mohammad; Jonathan May; Ekaterina Shutova; Steven Bethard; Marine Carpuat. Association for Computational Linguistics (ACL), 2018. p. 1094-1098 (NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop).

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

TY - GEN

T1 - ECNU at SemEval-2018 Task 12

T2 - 12th International Workshop on Semantic Evaluation, SemEval 2018, co-located with the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018

AU - Tian, Junfeng

AU - Lan, Man

AU - Wu, Yuanbin

PY - 2018

Y1 - 2018

N2 - This paper presents our submissions to SemEval 2018 Task 12: the Argument Reasoning Comprehension Task. We investigate an end-to-end attention-based neural network to represent the two lexically close candidate warrants. On the one hand, we extract their different parts as attention vectors to obtain distinguishable representations. On the other hand, we use their surrounds (i.e., claim, reason, debate context) as another attention vectors to get contextual representations, which work as final clues to select the correct warrant. Our model achieves 60.4% accuracy and ranks 3rd among 22 participating systems.

AB - This paper presents our submissions to SemEval 2018 Task 12: the Argument Reasoning Comprehension Task. We investigate an end-to-end attention-based neural network to represent the two lexically close candidate warrants. On the one hand, we extract their different parts as attention vectors to obtain distinguishable representations. On the other hand, we use their surrounds (i.e., claim, reason, debate context) as another attention vectors to get contextual representations, which work as final clues to select the correct warrant. Our model achieves 60.4% accuracy and ranks 3rd among 22 participating systems.

UR - https://www.scopus.com/pages/publications/85096580748

U2 - 10.18653/v1/s18-1184

DO - 10.18653/v1/s18-1184

M3 - 会议稿件

AN - SCOPUS:85096580748

T3 - NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop

SP - 1094

EP - 1098

BT - NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop

A2 - Apidianaki, Marianna

A2 - Mohammad, Saif M.

A2 - May, Jonathan

A2 - Shutova, Ekaterina

A2 - Bethard, Steven

A2 - Carpuat, Marine

PB - Association for Computational Linguistics (ACL)

Y2 - 5 June 2018 through 6 June 2018

ER -

Tian J, Lan M, Wu Y. ECNU at SemEval-2018 Task 12: An End-to-End Attention-based Neural Network for the Argument Reasoning Comprehension Task. In Apidianaki M, Apidianaki M, Mohammad SM, May J, Shutova E, Bethard S, Carpuat M, editors, NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop. Association for Computational Linguistics (ACL). 2018. p. 1094-1098. (NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop). doi: 10.18653/v1/s18-1184

ECNU at SemEval-2018 Task 12: An End-to-End Attention-based Neural Network for the Argument Reasoning Comprehension Task

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this