Learning adaptable patterns for passage reranking

Aliaksei Severyn, Massimo Nicosia, Alessandro Moschitti

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

25 Citations (Scopus)

Abstract

This paper proposes passage reranking models that (i) do not require manual feature engineering and (ii) greatly preserve accuracy, when changing application domain. Their main characteristic is the use of relational semantic structures representing questions and their answer passages. The relations are established using information from automatic classifiers, i.e., question category (QC) and focus classifiers (FC) and Named Entity Recognizers (NER). This way (i) effective structural relational patterns can be automatically learned with kernel machines; and (ii) structures are more invariant w.r.t. different domains, thus fostering adaptability.

Original languageEnglish
Title of host publicationCoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages75-83
Number of pages9
ISBN (Electronic)9781937284701
Publication statusPublished - 1 Jan 2013
Event17th Conference on Computational Natural Language Learning, CoNLL 2013 - Sofia, Bulgaria
Duration: 8 Aug 20139 Aug 2013

Publication series

NameCoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings

Conference

Conference17th Conference on Computational Natural Language Learning, CoNLL 2013
CountryBulgaria
CitySofia
Period8/8/139/8/13

Fingerprint

Classifiers
learning
Semantics
semantics
engineering

ASJC Scopus subject areas

  • Linguistics and Language
  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

Severyn, A., Nicosia, M., & Moschitti, A. (2013). Learning adaptable patterns for passage reranking. In CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings (pp. 75-83). (CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings). Association for Computational Linguistics (ACL).

Learning adaptable patterns for passage reranking. / Severyn, Aliaksei; Nicosia, Massimo; Moschitti, Alessandro.

CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings. Association for Computational Linguistics (ACL), 2013. p. 75-83 (CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings).

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

Severyn, A, Nicosia, M & Moschitti, A 2013, Learning adaptable patterns for passage reranking. in CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings. CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings, Association for Computational Linguistics (ACL), pp. 75-83, 17th Conference on Computational Natural Language Learning, CoNLL 2013, Sofia, Bulgaria, 8/8/13.
Severyn A, Nicosia M, Moschitti A. Learning adaptable patterns for passage reranking. In CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings. Association for Computational Linguistics (ACL). 2013. p. 75-83. (CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings).
Severyn, Aliaksei ; Nicosia, Massimo ; Moschitti, Alessandro. / Learning adaptable patterns for passage reranking. CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings. Association for Computational Linguistics (ACL), 2013. pp. 75-83 (CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings).
@inproceedings{ff5d12ecdc3242be876552332baea03a,
title = "Learning adaptable patterns for passage reranking",
abstract = "This paper proposes passage reranking models that (i) do not require manual feature engineering and (ii) greatly preserve accuracy, when changing application domain. Their main characteristic is the use of relational semantic structures representing questions and their answer passages. The relations are established using information from automatic classifiers, i.e., question category (QC) and focus classifiers (FC) and Named Entity Recognizers (NER). This way (i) effective structural relational patterns can be automatically learned with kernel machines; and (ii) structures are more invariant w.r.t. different domains, thus fostering adaptability.",
author = "Aliaksei Severyn and Massimo Nicosia and Alessandro Moschitti",
year = "2013",
month = "1",
day = "1",
language = "English",
series = "CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "75--83",
booktitle = "CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings",

}

TY - GEN

T1 - Learning adaptable patterns for passage reranking

AU - Severyn, Aliaksei

AU - Nicosia, Massimo

AU - Moschitti, Alessandro

PY - 2013/1/1

Y1 - 2013/1/1

N2 - This paper proposes passage reranking models that (i) do not require manual feature engineering and (ii) greatly preserve accuracy, when changing application domain. Their main characteristic is the use of relational semantic structures representing questions and their answer passages. The relations are established using information from automatic classifiers, i.e., question category (QC) and focus classifiers (FC) and Named Entity Recognizers (NER). This way (i) effective structural relational patterns can be automatically learned with kernel machines; and (ii) structures are more invariant w.r.t. different domains, thus fostering adaptability.

AB - This paper proposes passage reranking models that (i) do not require manual feature engineering and (ii) greatly preserve accuracy, when changing application domain. Their main characteristic is the use of relational semantic structures representing questions and their answer passages. The relations are established using information from automatic classifiers, i.e., question category (QC) and focus classifiers (FC) and Named Entity Recognizers (NER). This way (i) effective structural relational patterns can be automatically learned with kernel machines; and (ii) structures are more invariant w.r.t. different domains, thus fostering adaptability.

UR - http://www.scopus.com/inward/record.url?scp=84889598975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84889598975&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84889598975

T3 - CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings

SP - 75

EP - 83

BT - CoNLL 2013 - 17th Conference on Computational Natural Language Learning, Proceedings

PB - Association for Computational Linguistics (ACL)

ER -