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 num- ber 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.

RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations / Tymoshenko, Kateryna; Moschitti, Alessandro; Nicosia, Massimo; Severyn, Aliaksei. - ELETTRONICO. - (2017), pp. 79-84. ((Intervento presentato al convegno ACL 2017 tenutosi a Vancouver, Canada nel July 30 - August 4, 2017 [10.18653/v1/P17-4014].

RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations

Kateryna Tymoshenko;Alessandro Moschitti;Massimo Nicosia;
2017

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 num- ber 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.
Proceedings of the 55th Annual Meeting of the Association for ComputationalLinguistics, ACL 2017
USA
Association for Computational Linguistics (ACL)
978-1-945626-71-5
Tymoshenko, Kateryna; Moschitti, Alessandro; Nicosia, Massimo; Severyn, Aliaksei
RelTextRank: An Open Source Framework for Building Relational Syntactic-Semantic Text Pair Representations / Tymoshenko, Kateryna; Moschitti, Alessandro; Nicosia, Massimo; Severyn, Aliaksei. - ELETTRONICO. - (2017), pp. 79-84. ((Intervento presentato al convegno ACL 2017 tenutosi a Vancouver, Canada nel July 30 - August 4, 2017 [10.18653/v1/P17-4014].
File in questo prodotto:
File Dimensione Formato  
2017_ACL_RelTextRank.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Creative commons
Dimensione 357.55 kB
Formato Adobe PDF
357.55 kB Adobe PDF Visualizza/Apri
P17-4014.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 363.97 kB
Formato Adobe PDF
363.97 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11572/195413
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 1
social impact