ECNU at SemEval-2017 Task 3: Using Traditional and Deep Learning Methods to Address Community Question Answering Task

Guoshun Wu; Yixuan Sheng; Man Lan; Yuanbin Wu

doi:10.18653/v1/S17-2060

ECNU at SemEval-2017 Task 3: Using Traditional and Deep Learning Methods to Address Community Question Answering Task

Guoshun Wu
, Yixuan Sheng
, 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

21 Scopus citations

Abstract

This paper describes the systems we submitted to the task 3 (Community Question Answering) in SemEval 2017 which contains three subtasks on english corpora, i.e., subtask A: Question-Comment Similarity, subtask B: Question-Question Similarity, and subtask C: Question-External Comment Similarity. For subtask A, we combined two different methods to represent question-comment pair, i.e., supervised model using traditional features and Convolutional Neural Network. For subtask B, we utilized the information of snippets returned from Search Engine with question subject as query. For subtask C, we ranked the comments by multiplying the probability of the pair”related question õ comment” being Good by the reciprocal rank of the related question.

Original language	English
Title of host publication	ACL 2017 - 11th International Workshop on Semantic Evaluations, SemEval 2017, Proceedings of the Workshop
Publisher	Association for Computational Linguistics (ACL)
Pages	365-369
Number of pages	5
ISBN (Electronic)	9781945626555
DOIs	https://doi.org/10.18653/v1/S17-2060
State	Published - 2017
Event	11th International Workshop on Semantic Evaluations, SemEval 2017, co-located with the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada Duration: 3 Aug 2017 → 4 Aug 2017

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)	0736-587X

Conference

Conference	11th International Workshop on Semantic Evaluations, SemEval 2017, co-located with the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Country/Territory	Canada
City	Vancouver
Period	3/08/17 → 4/08/17

Access to Document

10.18653/v1/S17-2060

Cite this

Wu, G., Sheng, Y., Lan, M., & Wu, Y. (2017). ECNU at SemEval-2017 Task 3: Using Traditional and Deep Learning Methods to Address Community Question Answering Task. In ACL 2017 - 11th International Workshop on Semantic Evaluations, SemEval 2017, Proceedings of the Workshop (pp. 365-369). (Proceedings of the Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/S17-2060

Wu, Guoshun ; Sheng, Yixuan ; Lan, Man et al. / ECNU at SemEval-2017 Task 3 : Using Traditional and Deep Learning Methods to Address Community Question Answering Task. ACL 2017 - 11th International Workshop on Semantic Evaluations, SemEval 2017, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2017. pp. 365-369 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{c82cdc5bc32f4600bb2c0ee242a7fb50,

title = "ECNU at SemEval-2017 Task 3: Using Traditional and Deep Learning Methods to Address Community Question Answering Task",

abstract = "This paper describes the systems we submitted to the task 3 (Community Question Answering) in SemEval 2017 which contains three subtasks on english corpora, i.e., subtask A: Question-Comment Similarity, subtask B: Question-Question Similarity, and subtask C: Question-External Comment Similarity. For subtask A, we combined two different methods to represent question-comment pair, i.e., supervised model using traditional features and Convolutional Neural Network. For subtask B, we utilized the information of snippets returned from Search Engine with question subject as query. For subtask C, we ranked the comments by multiplying the probability of the pair”related question {\~o} comment” being Good by the reciprocal rank of the related question.",

author = "Guoshun Wu and Yixuan Sheng and Man Lan and Yuanbin Wu",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics; 11th International Workshop on Semantic Evaluations, SemEval 2017, co-located with the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 ; Conference date: 03-08-2017 Through 04-08-2017",

year = "2017",

doi = "10.18653/v1/S17-2060",

language = "英语",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

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

pages = "365--369",

booktitle = "ACL 2017 - 11th International Workshop on Semantic Evaluations, SemEval 2017, Proceedings of the Workshop",

address = "澳大利亚",

}

Wu, G, Sheng, Y, Lan, M & Wu, Y 2017, ECNU at SemEval-2017 Task 3: Using Traditional and Deep Learning Methods to Address Community Question Answering Task. in ACL 2017 - 11th International Workshop on Semantic Evaluations, SemEval 2017, Proceedings of the Workshop. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL), pp. 365-369, 11th International Workshop on Semantic Evaluations, SemEval 2017, co-located with the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, 3/08/17. https://doi.org/10.18653/v1/S17-2060

ECNU at SemEval-2017 Task 3: Using Traditional and Deep Learning Methods to Address Community Question Answering Task. / Wu, Guoshun; Sheng, Yixuan; Lan, Man et al.
ACL 2017 - 11th International Workshop on Semantic Evaluations, SemEval 2017, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2017. p. 365-369 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

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

TY - GEN

T1 - ECNU at SemEval-2017 Task 3

T2 - 11th International Workshop on Semantic Evaluations, SemEval 2017, co-located with the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017

AU - Wu, Guoshun

AU - Sheng, Yixuan

AU - Lan, Man

AU - Wu, Yuanbin

PY - 2017

Y1 - 2017

N2 - This paper describes the systems we submitted to the task 3 (Community Question Answering) in SemEval 2017 which contains three subtasks on english corpora, i.e., subtask A: Question-Comment Similarity, subtask B: Question-Question Similarity, and subtask C: Question-External Comment Similarity. For subtask A, we combined two different methods to represent question-comment pair, i.e., supervised model using traditional features and Convolutional Neural Network. For subtask B, we utilized the information of snippets returned from Search Engine with question subject as query. For subtask C, we ranked the comments by multiplying the probability of the pair”related question õ comment” being Good by the reciprocal rank of the related question.

AB - This paper describes the systems we submitted to the task 3 (Community Question Answering) in SemEval 2017 which contains three subtasks on english corpora, i.e., subtask A: Question-Comment Similarity, subtask B: Question-Question Similarity, and subtask C: Question-External Comment Similarity. For subtask A, we combined two different methods to represent question-comment pair, i.e., supervised model using traditional features and Convolutional Neural Network. For subtask B, we utilized the information of snippets returned from Search Engine with question subject as query. For subtask C, we ranked the comments by multiplying the probability of the pair”related question õ comment” being Good by the reciprocal rank of the related question.

UR - https://www.scopus.com/pages/publications/85084702135

U2 - 10.18653/v1/S17-2060

DO - 10.18653/v1/S17-2060

M3 - 会议稿件

AN - SCOPUS:85084702135

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 365

EP - 369

BT - ACL 2017 - 11th International Workshop on Semantic Evaluations, SemEval 2017, Proceedings of the Workshop

PB - Association for Computational Linguistics (ACL)

Y2 - 3 August 2017 through 4 August 2017

ER -

Wu G, Sheng Y, Lan M, Wu Y. ECNU at SemEval-2017 Task 3: Using Traditional and Deep Learning Methods to Address Community Question Answering Task. In ACL 2017 - 11th International Workshop on Semantic Evaluations, SemEval 2017, Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2017. p. 365-369. (Proceedings of the Annual Meeting of the Association for Computational Linguistics). doi: 10.18653/v1/S17-2060

ECNU at SemEval-2017 Task 3: Using Traditional and Deep Learning Methods to Address Community Question Answering Task

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this