Structural representations for learning relations between pairs of texts

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

22 Citations (Scopus)

Abstract

This paper studies the use of structural representations for learning relations between pairs of short texts (e.g., sentences or paragraphs) of the kind: The second text answers to, or conveys exactly the same information of, or is implied by, the first text. Engineering effective features that can capture syntactic and semantic relations between the constituents composing the target text pairs is rather complex. Thus, we define syntactic and semantic structures representing the text pairs and then apply graph and tree kernels to them for automatically engineering features in Support Vector Machines. We carry out an extensive comparative analysis of stateof-the-Art models for this type of relational learning. Our findings allow for achieving the highest accuracy in two different and important related tasks, i.e., Paraphrasing Identification and Textual Entailment Recognition.

Original languageEnglish
Title of host publicationACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages1003-1013
Number of pages11
Volume1
ISBN (Print)9781941643723
Publication statusPublished - 2015
Event53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 - Beijing, China
Duration: 26 Jul 201531 Jul 2015

Other

Other53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015
CountryChina
CityBeijing
Period26/7/1531/7/15

Fingerprint

Syntactics
Semantics
Support vector machines

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Filice, S., Martino, G., & Moschitti, A. (2015). Structural representations for learning relations between pairs of texts. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference (Vol. 1, pp. 1003-1013). Association for Computational Linguistics (ACL).

Structural representations for learning relations between pairs of texts. / Filice, Simone; Martino, Giovanni; Moschitti, Alessandro.

ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Vol. 1 Association for Computational Linguistics (ACL), 2015. p. 1003-1013.

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

Filice, S, Martino, G & Moschitti, A 2015, Structural representations for learning relations between pairs of texts. in ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. vol. 1, Association for Computational Linguistics (ACL), pp. 1003-1013, 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015, Beijing, China, 26/7/15.
Filice S, Martino G, Moschitti A. Structural representations for learning relations between pairs of texts. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Vol. 1. Association for Computational Linguistics (ACL). 2015. p. 1003-1013
Filice, Simone ; Martino, Giovanni ; Moschitti, Alessandro. / Structural representations for learning relations between pairs of texts. ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Vol. 1 Association for Computational Linguistics (ACL), 2015. pp. 1003-1013
@inproceedings{d9255a03feae4895a6092b919635bd39,
title = "Structural representations for learning relations between pairs of texts",
abstract = "This paper studies the use of structural representations for learning relations between pairs of short texts (e.g., sentences or paragraphs) of the kind: The second text answers to, or conveys exactly the same information of, or is implied by, the first text. Engineering effective features that can capture syntactic and semantic relations between the constituents composing the target text pairs is rather complex. Thus, we define syntactic and semantic structures representing the text pairs and then apply graph and tree kernels to them for automatically engineering features in Support Vector Machines. We carry out an extensive comparative analysis of stateof-the-Art models for this type of relational learning. Our findings allow for achieving the highest accuracy in two different and important related tasks, i.e., Paraphrasing Identification and Textual Entailment Recognition.",
author = "Simone Filice and Giovanni Martino and Alessandro Moschitti",
year = "2015",
language = "English",
isbn = "9781941643723",
volume = "1",
pages = "1003--1013",
booktitle = "ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Structural representations for learning relations between pairs of texts

AU - Filice, Simone

AU - Martino, Giovanni

AU - Moschitti, Alessandro

PY - 2015

Y1 - 2015

N2 - This paper studies the use of structural representations for learning relations between pairs of short texts (e.g., sentences or paragraphs) of the kind: The second text answers to, or conveys exactly the same information of, or is implied by, the first text. Engineering effective features that can capture syntactic and semantic relations between the constituents composing the target text pairs is rather complex. Thus, we define syntactic and semantic structures representing the text pairs and then apply graph and tree kernels to them for automatically engineering features in Support Vector Machines. We carry out an extensive comparative analysis of stateof-the-Art models for this type of relational learning. Our findings allow for achieving the highest accuracy in two different and important related tasks, i.e., Paraphrasing Identification and Textual Entailment Recognition.

AB - This paper studies the use of structural representations for learning relations between pairs of short texts (e.g., sentences or paragraphs) of the kind: The second text answers to, or conveys exactly the same information of, or is implied by, the first text. Engineering effective features that can capture syntactic and semantic relations between the constituents composing the target text pairs is rather complex. Thus, we define syntactic and semantic structures representing the text pairs and then apply graph and tree kernels to them for automatically engineering features in Support Vector Machines. We carry out an extensive comparative analysis of stateof-the-Art models for this type of relational learning. Our findings allow for achieving the highest accuracy in two different and important related tasks, i.e., Paraphrasing Identification and Textual Entailment Recognition.

UR - http://www.scopus.com/inward/record.url?scp=84943805083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943805083&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781941643723

VL - 1

SP - 1003

EP - 1013

BT - ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -