Reltextrank

An open source framework for building relational syntactic-semantic text pair representations

Kateryna Tymoshenko, Alessandro Moschitti, Massimo Nicosia, Aliaksei Severyn

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

1 Citation (Scopus)

Abstract

We present a highly-flexible UIMA-based pipeline for developing structural kernel-based systems for relational learning from text, i.e., for generating training and test data for ranking, classifying short text pairs or measuring similarity between pieces of text. For example, the proposed pipeline can represent an input question and answer sentence pairs as syntactic-semantic structures, enriching them with relational information, e.g., links between question class, focus and named entities, and serializes them as training and test files for the tree kernel-based reranking framework. The pipeline generates a number of dependency and shallow chunk-based representations shown to achieve competitive results in previous work. It also enables easy evaluation of the models thanks to cross-validation facilities.

Original languageEnglish
Title of host publicationACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of System Demonstrations
PublisherAssociation for Computational Linguistics (ACL)
Pages79-84
Number of pages6
ISBN (Print)9781945626715
DOIs
Publication statusPublished - 1 Jan 2017
Event55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada
Duration: 30 Jul 20174 Aug 2017

Other

Other55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
CountryCanada
CityVancouver
Period30/7/174/8/17

Fingerprint

Syntactics
Pipelines
Semantics
semantics
ranking
evaluation
learning
Open Source
Syntax
Kernel

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language
  • Artificial Intelligence
  • Software

Cite this

Tymoshenko, K., Moschitti, A., Nicosia, M., & Severyn, A. (2017). Reltextrank: An open source framework for building relational syntactic-semantic text pair representations. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of System Demonstrations (pp. 79-84). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/P17-4014

Reltextrank : An open source framework for building relational syntactic-semantic text pair representations. / Tymoshenko, Kateryna; Moschitti, Alessandro; Nicosia, Massimo; Severyn, Aliaksei.

ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of System Demonstrations. Association for Computational Linguistics (ACL), 2017. p. 79-84.

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

Tymoshenko, K, Moschitti, A, Nicosia, M & Severyn, A 2017, Reltextrank: An open source framework for building relational syntactic-semantic text pair representations. in ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of System Demonstrations. Association for Computational Linguistics (ACL), pp. 79-84, 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, 30/7/17. https://doi.org/10.18653/v1/P17-4014
Tymoshenko K, Moschitti A, Nicosia M, Severyn A. Reltextrank: An open source framework for building relational syntactic-semantic text pair representations. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of System Demonstrations. Association for Computational Linguistics (ACL). 2017. p. 79-84 https://doi.org/10.18653/v1/P17-4014
Tymoshenko, Kateryna ; Moschitti, Alessandro ; Nicosia, Massimo ; Severyn, Aliaksei. / Reltextrank : An open source framework for building relational syntactic-semantic text pair representations. ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of System Demonstrations. Association for Computational Linguistics (ACL), 2017. pp. 79-84
@inproceedings{9fb53dfe76ce4fb3bc1b4cee7b6024c8,
title = "Reltextrank: An open source framework for building relational syntactic-semantic text pair representations",
abstract = "We present a highly-flexible UIMA-based pipeline for developing structural kernel-based systems for relational learning from text, i.e., for generating training and test data for ranking, classifying short text pairs or measuring similarity between pieces of text. For example, the proposed pipeline can represent an input question and answer sentence pairs as syntactic-semantic structures, enriching them with relational information, e.g., links between question class, focus and named entities, and serializes them as training and test files for the tree kernel-based reranking framework. The pipeline generates a number of dependency and shallow chunk-based representations shown to achieve competitive results in previous work. It also enables easy evaluation of the models thanks to cross-validation facilities.",
author = "Kateryna Tymoshenko and Alessandro Moschitti and Massimo Nicosia and Aliaksei Severyn",
year = "2017",
month = "1",
day = "1",
doi = "10.18653/v1/P17-4014",
language = "English",
isbn = "9781945626715",
pages = "79--84",
booktitle = "ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of System Demonstrations",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Reltextrank

T2 - An open source framework for building relational syntactic-semantic text pair representations

AU - Tymoshenko, Kateryna

AU - Moschitti, Alessandro

AU - Nicosia, Massimo

AU - Severyn, Aliaksei

PY - 2017/1/1

Y1 - 2017/1/1

N2 - We present a highly-flexible UIMA-based pipeline for developing structural kernel-based systems for relational learning from text, i.e., for generating training and test data for ranking, classifying short text pairs or measuring similarity between pieces of text. For example, the proposed pipeline can represent an input question and answer sentence pairs as syntactic-semantic structures, enriching them with relational information, e.g., links between question class, focus and named entities, and serializes them as training and test files for the tree kernel-based reranking framework. The pipeline generates a number of dependency and shallow chunk-based representations shown to achieve competitive results in previous work. It also enables easy evaluation of the models thanks to cross-validation facilities.

AB - We present a highly-flexible UIMA-based pipeline for developing structural kernel-based systems for relational learning from text, i.e., for generating training and test data for ranking, classifying short text pairs or measuring similarity between pieces of text. For example, the proposed pipeline can represent an input question and answer sentence pairs as syntactic-semantic structures, enriching them with relational information, e.g., links between question class, focus and named entities, and serializes them as training and test files for the tree kernel-based reranking framework. The pipeline generates a number of dependency and shallow chunk-based representations shown to achieve competitive results in previous work. It also enables easy evaluation of the models thanks to cross-validation facilities.

UR - http://www.scopus.com/inward/record.url?scp=85054338796&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054338796&partnerID=8YFLogxK

U2 - 10.18653/v1/P17-4014

DO - 10.18653/v1/P17-4014

M3 - Conference contribution

SN - 9781945626715

SP - 79

EP - 84

BT - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of System Demonstrations

PB - Association for Computational Linguistics (ACL)

ER -