Automatic feature engineering for answer selection and extraction

Aliaksei Severyn, Alessandro Moschitti

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

60 Citations (Scopus)

Abstract

This paper proposes a framework for automatically engineering features for two important tasks of question answering: answer sentence selection and answer extraction. We represent question and answer sentence pairs with linguistic structures enriched by semantic information, where the latter is produced by automatic classifiers, e.g., question classifier and Named Entity Recognizer. Tree kernels applied to such structures enable a simple way to generate highly discriminative structural features that combine syntactic and semantic information encoded in the input trees. We conduct experiments on a public benchmark from TREC to compare with previous systems for answer sentence selection and answer extraction. The results show that our models greatly improve on the state of the art, e.g., up to 22% on F1 (relative improvement) for answer extraction, while using no additional resources and no manual feature engineering.

Original languageEnglish
Title of host publicationEMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages458-467
Number of pages10
ISBN (Print)9781937284978
Publication statusPublished - 2013
Event2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013 - Seattle, United States
Duration: 18 Oct 201321 Oct 2013

Other

Other2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013
CountryUnited States
CitySeattle
Period18/10/1321/10/13

Fingerprint

Classifiers
Semantics
Syntactics
Linguistics
Experiments

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Information Systems
  • Computer Vision and Pattern Recognition

Cite this

Severyn, A., & Moschitti, A. (2013). Automatic feature engineering for answer selection and extraction. In EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 458-467). Association for Computational Linguistics (ACL).

Automatic feature engineering for answer selection and extraction. / Severyn, Aliaksei; Moschitti, Alessandro.

EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2013. p. 458-467.

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

Severyn, A & Moschitti, A 2013, Automatic feature engineering for answer selection and extraction. in EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), pp. 458-467, 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, Seattle, United States, 18/10/13.
Severyn A, Moschitti A. Automatic feature engineering for answer selection and extraction. In EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2013. p. 458-467
Severyn, Aliaksei ; Moschitti, Alessandro. / Automatic feature engineering for answer selection and extraction. EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2013. pp. 458-467
@inproceedings{a02f48325cc24fd182c8bb0ca92da63b,
title = "Automatic feature engineering for answer selection and extraction",
abstract = "This paper proposes a framework for automatically engineering features for two important tasks of question answering: answer sentence selection and answer extraction. We represent question and answer sentence pairs with linguistic structures enriched by semantic information, where the latter is produced by automatic classifiers, e.g., question classifier and Named Entity Recognizer. Tree kernels applied to such structures enable a simple way to generate highly discriminative structural features that combine syntactic and semantic information encoded in the input trees. We conduct experiments on a public benchmark from TREC to compare with previous systems for answer sentence selection and answer extraction. The results show that our models greatly improve on the state of the art, e.g., up to 22{\%} on F1 (relative improvement) for answer extraction, while using no additional resources and no manual feature engineering.",
author = "Aliaksei Severyn and Alessandro Moschitti",
year = "2013",
language = "English",
isbn = "9781937284978",
pages = "458--467",
booktitle = "EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Automatic feature engineering for answer selection and extraction

AU - Severyn, Aliaksei

AU - Moschitti, Alessandro

PY - 2013

Y1 - 2013

N2 - This paper proposes a framework for automatically engineering features for two important tasks of question answering: answer sentence selection and answer extraction. We represent question and answer sentence pairs with linguistic structures enriched by semantic information, where the latter is produced by automatic classifiers, e.g., question classifier and Named Entity Recognizer. Tree kernels applied to such structures enable a simple way to generate highly discriminative structural features that combine syntactic and semantic information encoded in the input trees. We conduct experiments on a public benchmark from TREC to compare with previous systems for answer sentence selection and answer extraction. The results show that our models greatly improve on the state of the art, e.g., up to 22% on F1 (relative improvement) for answer extraction, while using no additional resources and no manual feature engineering.

AB - This paper proposes a framework for automatically engineering features for two important tasks of question answering: answer sentence selection and answer extraction. We represent question and answer sentence pairs with linguistic structures enriched by semantic information, where the latter is produced by automatic classifiers, e.g., question classifier and Named Entity Recognizer. Tree kernels applied to such structures enable a simple way to generate highly discriminative structural features that combine syntactic and semantic information encoded in the input trees. We conduct experiments on a public benchmark from TREC to compare with previous systems for answer sentence selection and answer extraction. The results show that our models greatly improve on the state of the art, e.g., up to 22% on F1 (relative improvement) for answer extraction, while using no additional resources and no manual feature engineering.

UR - http://www.scopus.com/inward/record.url?scp=84906925685&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906925685&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781937284978

SP - 458

EP - 467

BT - EMNLP 2013 - 2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -