Tohoku at SemEval-2016 task 6: Feature-based model versus convolutional neural network for stance detection

Yuki Igarashi; Hiroya Komatsu; Sosuke Kobayashi; Naoaki Okazaki; Kentaro Inui

doi:10.18653/v1/s16-1065

Tohoku at SemEval-2016 task 6: Feature-based model versus convolutional neural network for stance detection

Yuki Igarashi, Hiroya Komatsu, Sosuke Kobayashi, Naoaki Okazaki, Kentaro Inui

INF - System Information Sciences

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

7 Citations (Scopus)

Abstract

In this paper, we compare feature-based and Neural Network-based approaches on the supervised stance classification task for tweets in SemEval-2016 Task 6 Subtask A (Mohammad et al., 2016). In the feature-based approach, we use external resources such as lexicons and crawled texts. The Neural Network based approach employs Convolutional Neural Network (CNN). Our results show that the feature-based model outperformed the CNN model on the test data although the CNN model was better than the feature-based model in the cross validation on the training data.

Original language	English
Title of host publication	SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings
Publisher	Association for Computational Linguistics (ACL)
Pages	401-407
Number of pages	7
ISBN (Electronic)	9781941643952
DOIs	https://doi.org/10.18653/v1/s16-1065
Publication status	Published - 2016
Event	10th International Workshop on Semantic Evaluation, SemEval 2016 - San Diego, United States Duration: 2016 Jun 16 → 2016 Jun 17

Publication series

Name	SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings

Other

Other	10th International Workshop on Semantic Evaluation, SemEval 2016
Country	United States
City	San Diego
Period	16/6/16 → 16/6/17

ASJC Scopus subject areas

Theoretical Computer Science
Computational Theory and Mathematics
Computer Science Applications

Access to Document

10.18653/v1/s16-1065

Fingerprint Dive into the research topics of 'Tohoku at SemEval-2016 task 6: Feature-based model versus convolutional neural network for stance detection'. Together they form a unique fingerprint.

Cite this

Igarashi, Y., Komatsu, H., Kobayashi, S., Okazaki, N., & Inui, K. (2016). Tohoku at SemEval-2016 task 6: Feature-based model versus convolutional neural network for stance detection. In SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings (pp. 401-407). (SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/s16-1065

Tohoku at SemEval-2016 task 6 : Feature-based model versus convolutional neural network for stance detection. / Igarashi, Yuki; Komatsu, Hiroya; Kobayashi, Sosuke; Okazaki, Naoaki; Inui, Kentaro.

SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings. Association for Computational Linguistics (ACL), 2016. p. 401-407 (SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings).

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

Igarashi, Y, Komatsu, H, Kobayashi, S, Okazaki, N & Inui, K 2016, Tohoku at SemEval-2016 task 6: Feature-based model versus convolutional neural network for stance detection. in SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings. SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings, Association for Computational Linguistics (ACL), pp. 401-407, 10th International Workshop on Semantic Evaluation, SemEval 2016, San Diego, United States, 16/6/16. https://doi.org/10.18653/v1/s16-1065

Igarashi Y, Komatsu H, Kobayashi S, Okazaki N, Inui K. Tohoku at SemEval-2016 task 6: Feature-based model versus convolutional neural network for stance detection. In SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings. Association for Computational Linguistics (ACL). 2016. p. 401-407. (SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings). https://doi.org/10.18653/v1/s16-1065

Igarashi, Yuki ; Komatsu, Hiroya ; Kobayashi, Sosuke ; Okazaki, Naoaki ; Inui, Kentaro. / Tohoku at SemEval-2016 task 6 : Feature-based model versus convolutional neural network for stance detection. SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings. Association for Computational Linguistics (ACL), 2016. pp. 401-407 (SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings).

@inproceedings{91535aa2ebd547c7869784ff552202a6,

title = "Tohoku at SemEval-2016 task 6: Feature-based model versus convolutional neural network for stance detection",

abstract = "In this paper, we compare feature-based and Neural Network-based approaches on the supervised stance classification task for tweets in SemEval-2016 Task 6 Subtask A (Mohammad et al., 2016). In the feature-based approach, we use external resources such as lexicons and crawled texts. The Neural Network based approach employs Convolutional Neural Network (CNN). Our results show that the feature-based model outperformed the CNN model on the test data although the CNN model was better than the feature-based model in the cross validation on the training data.",

author = "Yuki Igarashi and Hiroya Komatsu and Sosuke Kobayashi and Naoaki Okazaki and Kentaro Inui",

year = "2016",

doi = "10.18653/v1/s16-1065",

language = "English",

series = "SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings",

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

pages = "401--407",

booktitle = "SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings",

note = "10th International Workshop on Semantic Evaluation, SemEval 2016 ; Conference date: 16-06-2016 Through 17-06-2016",

}

TY - GEN

T1 - Tohoku at SemEval-2016 task 6

T2 - 10th International Workshop on Semantic Evaluation, SemEval 2016

AU - Igarashi, Yuki

AU - Komatsu, Hiroya

AU - Kobayashi, Sosuke

AU - Okazaki, Naoaki

AU - Inui, Kentaro

PY - 2016

Y1 - 2016

N2 - In this paper, we compare feature-based and Neural Network-based approaches on the supervised stance classification task for tweets in SemEval-2016 Task 6 Subtask A (Mohammad et al., 2016). In the feature-based approach, we use external resources such as lexicons and crawled texts. The Neural Network based approach employs Convolutional Neural Network (CNN). Our results show that the feature-based model outperformed the CNN model on the test data although the CNN model was better than the feature-based model in the cross validation on the training data.

AB - In this paper, we compare feature-based and Neural Network-based approaches on the supervised stance classification task for tweets in SemEval-2016 Task 6 Subtask A (Mohammad et al., 2016). In the feature-based approach, we use external resources such as lexicons and crawled texts. The Neural Network based approach employs Convolutional Neural Network (CNN). Our results show that the feature-based model outperformed the CNN model on the test data although the CNN model was better than the feature-based model in the cross validation on the training data.

UR - http://www.scopus.com/inward/record.url?scp=85035794223&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85035794223&partnerID=8YFLogxK

U2 - 10.18653/v1/s16-1065

DO - 10.18653/v1/s16-1065

M3 - Conference contribution

AN - SCOPUS:85035794223

T3 - SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings

SP - 401

EP - 407

BT - SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings

PB - Association for Computational Linguistics (ACL)

Y2 - 16 June 2016 through 17 June 2016

ER -