Learning semantic textual similarity with structural representations

Aliaksei Severyn, Massimo Nicosia, Alessandro Moschitti

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

15 Citations (Scopus)

Abstract

Measuring semantic textual similarity (STS) is at the cornerstone of many NLP applications. Different from the majority of approaches, where a large number of pairwise similarity features are used to represent a text pair, our model features the following: (i) it directly encodes input texts into relational syntactic structures; (ii) relies on tree kernels to handle feature engineering automatically; (iii) combines both structural and feature vector representations in a single scoring model, i.e., in Support Vector Regression (SVR); and (iv) delivers significant improvement over the best STS systems.

Original languageEnglish
Title of host publicationACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages714-718
Number of pages5
Volume2
ISBN (Print)9781937284510
Publication statusPublished - 1 Jan 2013
Event51st Annual Meeting of the Association for Computational Linguistics, ACL 2013 - Sofia, Bulgaria
Duration: 4 Aug 20139 Aug 2013

Other

Other51st Annual Meeting of the Association for Computational Linguistics, ACL 2013
CountryBulgaria
CitySofia
Period4/8/139/8/13

Fingerprint

semantics
learning
engineering
regression
Syntactic Structure
Kernel
Scoring
Natural Language Processing

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Severyn, A., Nicosia, M., & Moschitti, A. (2013). Learning semantic textual similarity with structural representations. In ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Vol. 2, pp. 714-718). Association for Computational Linguistics (ACL).

Learning semantic textual similarity with structural representations. / Severyn, Aliaksei; Nicosia, Massimo; Moschitti, Alessandro.

ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Vol. 2 Association for Computational Linguistics (ACL), 2013. p. 714-718.

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

Severyn, A, Nicosia, M & Moschitti, A 2013, Learning semantic textual similarity with structural representations. in ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. vol. 2, Association for Computational Linguistics (ACL), pp. 714-718, 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013, Sofia, Bulgaria, 4/8/13.
Severyn A, Nicosia M, Moschitti A. Learning semantic textual similarity with structural representations. In ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Vol. 2. Association for Computational Linguistics (ACL). 2013. p. 714-718
Severyn, Aliaksei ; Nicosia, Massimo ; Moschitti, Alessandro. / Learning semantic textual similarity with structural representations. ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Vol. 2 Association for Computational Linguistics (ACL), 2013. pp. 714-718
@inproceedings{92f96daf5c284e0badb89b6d3f75c3c5,
title = "Learning semantic textual similarity with structural representations",
abstract = "Measuring semantic textual similarity (STS) is at the cornerstone of many NLP applications. Different from the majority of approaches, where a large number of pairwise similarity features are used to represent a text pair, our model features the following: (i) it directly encodes input texts into relational syntactic structures; (ii) relies on tree kernels to handle feature engineering automatically; (iii) combines both structural and feature vector representations in a single scoring model, i.e., in Support Vector Regression (SVR); and (iv) delivers significant improvement over the best STS systems.",
author = "Aliaksei Severyn and Massimo Nicosia and Alessandro Moschitti",
year = "2013",
month = "1",
day = "1",
language = "English",
isbn = "9781937284510",
volume = "2",
pages = "714--718",
booktitle = "ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Learning semantic textual similarity with structural representations

AU - Severyn, Aliaksei

AU - Nicosia, Massimo

AU - Moschitti, Alessandro

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Measuring semantic textual similarity (STS) is at the cornerstone of many NLP applications. Different from the majority of approaches, where a large number of pairwise similarity features are used to represent a text pair, our model features the following: (i) it directly encodes input texts into relational syntactic structures; (ii) relies on tree kernels to handle feature engineering automatically; (iii) combines both structural and feature vector representations in a single scoring model, i.e., in Support Vector Regression (SVR); and (iv) delivers significant improvement over the best STS systems.

AB - Measuring semantic textual similarity (STS) is at the cornerstone of many NLP applications. Different from the majority of approaches, where a large number of pairwise similarity features are used to represent a text pair, our model features the following: (i) it directly encodes input texts into relational syntactic structures; (ii) relies on tree kernels to handle feature engineering automatically; (iii) combines both structural and feature vector representations in a single scoring model, i.e., in Support Vector Regression (SVR); and (iv) delivers significant improvement over the best STS systems.

UR - http://www.scopus.com/inward/record.url?scp=84907313623&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907313623&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84907313623

SN - 9781937284510

VL - 2

SP - 714

EP - 718

BT - ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -