Reference scope identification for citances by classification with text similarity measures

Jen Yuan Yen, Tien Yu Hsu, Cheng Jung Tsai, Pei Cheng Cheng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper targets at the first step towards generating citation summaries - to identify the reference scope (i.e., cited text spans) for citances. We present a novel classification-based method that converts the task into binary classification which distinguishes cited and non-cited pairs of citances and reference sentences. The method models pairs of citances and reference sentences as feature vectors where citation-dependent and citation-independent features based on the semantic similarity between texts and the significance of texts are explored. Such vector representations are utilized to train a binary classifier. For a citance, once the set of reference sentences classified as the cited sentences are collected, a heuristic-based filtering strategy is applied to refine the output. The method is evaluated using the CL-SciSumm 2016 datasets and found to perform well with competitive results.

Original languageEnglish
Title of host publicationProceedings of 2017 6th International Conference on Software and Computer Applications, ICSCA 2017
PublisherAssociation for Computing Machinery
Pages87-91
Number of pages5
ISBN (Electronic)9781450348577
DOIs
Publication statusPublished - 2017 Feb 26
Event6th International Conference on Software and Computer Applications, ICSCA 2017 - Bangkok, Thailand
Duration: 2017 Feb 262017 Feb 28

Publication series

NameACM International Conference Proceeding Series

Other

Other6th International Conference on Software and Computer Applications, ICSCA 2017
CountryThailand
CityBangkok
Period17-02-2617-02-28

Fingerprint

Classifiers
Semantics

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Yen, J. Y., Hsu, T. Y., Tsai, C. J., & Cheng, P. C. (2017). Reference scope identification for citances by classification with text similarity measures. In Proceedings of 2017 6th International Conference on Software and Computer Applications, ICSCA 2017 (pp. 87-91). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3056662.3056692
Yen, Jen Yuan ; Hsu, Tien Yu ; Tsai, Cheng Jung ; Cheng, Pei Cheng. / Reference scope identification for citances by classification with text similarity measures. Proceedings of 2017 6th International Conference on Software and Computer Applications, ICSCA 2017. Association for Computing Machinery, 2017. pp. 87-91 (ACM International Conference Proceeding Series).
@inproceedings{5f9df6c7275245c0b5ff893e4b2cb28c,
title = "Reference scope identification for citances by classification with text similarity measures",
abstract = "This paper targets at the first step towards generating citation summaries - to identify the reference scope (i.e., cited text spans) for citances. We present a novel classification-based method that converts the task into binary classification which distinguishes cited and non-cited pairs of citances and reference sentences. The method models pairs of citances and reference sentences as feature vectors where citation-dependent and citation-independent features based on the semantic similarity between texts and the significance of texts are explored. Such vector representations are utilized to train a binary classifier. For a citance, once the set of reference sentences classified as the cited sentences are collected, a heuristic-based filtering strategy is applied to refine the output. The method is evaluated using the CL-SciSumm 2016 datasets and found to perform well with competitive results.",
author = "Yen, {Jen Yuan} and Hsu, {Tien Yu} and Tsai, {Cheng Jung} and Cheng, {Pei Cheng}",
year = "2017",
month = "2",
day = "26",
doi = "10.1145/3056662.3056692",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "87--91",
booktitle = "Proceedings of 2017 6th International Conference on Software and Computer Applications, ICSCA 2017",

}

Yen, JY, Hsu, TY, Tsai, CJ & Cheng, PC 2017, Reference scope identification for citances by classification with text similarity measures. in Proceedings of 2017 6th International Conference on Software and Computer Applications, ICSCA 2017. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 87-91, 6th International Conference on Software and Computer Applications, ICSCA 2017, Bangkok, Thailand, 17-02-26. https://doi.org/10.1145/3056662.3056692

Reference scope identification for citances by classification with text similarity measures. / Yen, Jen Yuan; Hsu, Tien Yu; Tsai, Cheng Jung; Cheng, Pei Cheng.

Proceedings of 2017 6th International Conference on Software and Computer Applications, ICSCA 2017. Association for Computing Machinery, 2017. p. 87-91 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Reference scope identification for citances by classification with text similarity measures

AU - Yen, Jen Yuan

AU - Hsu, Tien Yu

AU - Tsai, Cheng Jung

AU - Cheng, Pei Cheng

PY - 2017/2/26

Y1 - 2017/2/26

N2 - This paper targets at the first step towards generating citation summaries - to identify the reference scope (i.e., cited text spans) for citances. We present a novel classification-based method that converts the task into binary classification which distinguishes cited and non-cited pairs of citances and reference sentences. The method models pairs of citances and reference sentences as feature vectors where citation-dependent and citation-independent features based on the semantic similarity between texts and the significance of texts are explored. Such vector representations are utilized to train a binary classifier. For a citance, once the set of reference sentences classified as the cited sentences are collected, a heuristic-based filtering strategy is applied to refine the output. The method is evaluated using the CL-SciSumm 2016 datasets and found to perform well with competitive results.

AB - This paper targets at the first step towards generating citation summaries - to identify the reference scope (i.e., cited text spans) for citances. We present a novel classification-based method that converts the task into binary classification which distinguishes cited and non-cited pairs of citances and reference sentences. The method models pairs of citances and reference sentences as feature vectors where citation-dependent and citation-independent features based on the semantic similarity between texts and the significance of texts are explored. Such vector representations are utilized to train a binary classifier. For a citance, once the set of reference sentences classified as the cited sentences are collected, a heuristic-based filtering strategy is applied to refine the output. The method is evaluated using the CL-SciSumm 2016 datasets and found to perform well with competitive results.

UR - http://www.scopus.com/inward/record.url?scp=85019438353&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019438353&partnerID=8YFLogxK

U2 - 10.1145/3056662.3056692

DO - 10.1145/3056662.3056692

M3 - Conference contribution

T3 - ACM International Conference Proceeding Series

SP - 87

EP - 91

BT - Proceedings of 2017 6th International Conference on Software and Computer Applications, ICSCA 2017

PB - Association for Computing Machinery

ER -

Yen JY, Hsu TY, Tsai CJ, Cheng PC. Reference scope identification for citances by classification with text similarity measures. In Proceedings of 2017 6th International Conference on Software and Computer Applications, ICSCA 2017. Association for Computing Machinery. 2017. p. 87-91. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3056662.3056692