Learning to re-rank questions in community question answering using advanced features

Giovanni Martino; Alberto Barron; Salvatore Romeo; Antonio Uva; Alessandro Moschitti

doi:10.1145/2983323.2983893

Learning to re-rank questions in community question answering using advanced features

Giovanni Martino, Alberto Barron, Salvatore Romeo, Antonio Uva, Alessandro Moschitti

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

10 Citations (Scopus)

Abstract

We study the impact of different types of features for question ranking in community Question Answering: bag-of-words models (BoW), syntactic tree kernels (TKs) and rank features. It should be noted that structural kernels have never been applied to the question reranking task, i.e., question to question similarity, where they have to model paraphrase relations. Additionally, the informal text, typically present in forums, poses new challenges to the use of TKs. We compare our learning to rank (L2R) algorithms against a strong baseline given by the Google rank (GR). The results show that (i) our shallow structures used in TKs are robust enough to noisy data and (ii) improving GR requires effective BoW features and TKs along with an accurate model of GR features in the used L2R algorithm.

Original language	English
Title of host publication	CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management
Publisher	Association for Computing Machinery
Pages	1997-2000
Number of pages	4
Volume	24-28-October-2016
ISBN (Electronic)	9781450340731
DOIs	https://doi.org/10.1145/2983323.2983893
Publication status	Published - 24 Oct 2016
Event	25th ACM International Conference on Information and Knowledge Management, CIKM 2016 - Indianapolis, United States Duration: 24 Oct 2016 → 28 Oct 2016

Other

Other	25th ACM International Conference on Information and Knowledge Management, CIKM 2016
Country	United States
City	Indianapolis
Period	24/10/16 → 28/10/16

Fingerprint

Keywords

Community question answering
Learning to rank
Syntactic structures

ASJC Scopus subject areas

Business, Management and Accounting(all)
Decision Sciences(all)

Cite this

Martino, G., Barron, A., Romeo, S., Uva, A., & Moschitti, A. (2016). Learning to re-rank questions in community question answering using advanced features. In CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management (Vol. 24-28-October-2016, pp. 1997-2000). Association for Computing Machinery. https://doi.org/10.1145/2983323.2983893

Learning to re-rank questions in community question answering using advanced features. / Martino, Giovanni ; Barron, Alberto ; Romeo, Salvatore; Uva, Antonio; Moschitti, Alessandro.

CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Vol. 24-28-October-2016 Association for Computing Machinery, 2016. p. 1997-2000.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Martino, G , Barron, A , Romeo, S, Uva, A & Moschitti, A 2016, Learning to re-rank questions in community question answering using advanced features. in CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. vol. 24-28-October-2016, Association for Computing Machinery, pp. 1997-2000, 25th ACM International Conference on Information and Knowledge Management, CIKM 2016, Indianapolis, United States, 24/10/16. https://doi.org/10.1145/2983323.2983893

@inproceedings{6ac36856abd947999c1bede204849d5a,

title = "Learning to re-rank questions in community question answering using advanced features",

abstract = "We study the impact of different types of features for question ranking in community Question Answering: bag-of-words models (BoW), syntactic tree kernels (TKs) and rank features. It should be noted that structural kernels have never been applied to the question reranking task, i.e., question to question similarity, where they have to model paraphrase relations. Additionally, the informal text, typically present in forums, poses new challenges to the use of TKs. We compare our learning to rank (L2R) algorithms against a strong baseline given by the Google rank (GR). The results show that (i) our shallow structures used in TKs are robust enough to noisy data and (ii) improving GR requires effective BoW features and TKs along with an accurate model of GR features in the used L2R algorithm.",

keywords = "Community question answering, Learning to rank, Syntactic structures",

author = "Giovanni Martino and Alberto Barron and Salvatore Romeo and Antonio Uva and Alessandro Moschitti",

year = "2016",

month = oct

day = "24",

doi = "10.1145/2983323.2983893",

language = "English",

volume = "24-28-October-2016",

pages = "1997--2000",

booktitle = "CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management",

publisher = "Association for Computing Machinery",

note = "25th ACM International Conference on Information and Knowledge Management, CIKM 2016 ; Conference date: 24-10-2016 Through 28-10-2016",

}

TY - GEN

T1 - Learning to re-rank questions in community question answering using advanced features

AU - Martino, Giovanni

AU - Barron, Alberto

AU - Romeo, Salvatore

AU - Uva, Antonio

AU - Moschitti, Alessandro

PY - 2016/10/24

Y1 - 2016/10/24

N2 - We study the impact of different types of features for question ranking in community Question Answering: bag-of-words models (BoW), syntactic tree kernels (TKs) and rank features. It should be noted that structural kernels have never been applied to the question reranking task, i.e., question to question similarity, where they have to model paraphrase relations. Additionally, the informal text, typically present in forums, poses new challenges to the use of TKs. We compare our learning to rank (L2R) algorithms against a strong baseline given by the Google rank (GR). The results show that (i) our shallow structures used in TKs are robust enough to noisy data and (ii) improving GR requires effective BoW features and TKs along with an accurate model of GR features in the used L2R algorithm.

AB - We study the impact of different types of features for question ranking in community Question Answering: bag-of-words models (BoW), syntactic tree kernels (TKs) and rank features. It should be noted that structural kernels have never been applied to the question reranking task, i.e., question to question similarity, where they have to model paraphrase relations. Additionally, the informal text, typically present in forums, poses new challenges to the use of TKs. We compare our learning to rank (L2R) algorithms against a strong baseline given by the Google rank (GR). The results show that (i) our shallow structures used in TKs are robust enough to noisy data and (ii) improving GR requires effective BoW features and TKs along with an accurate model of GR features in the used L2R algorithm.

KW - Community question answering

KW - Learning to rank

KW - Syntactic structures

UR - http://www.scopus.com/inward/record.url?scp=84996558218&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84996558218&partnerID=8YFLogxK

U2 - 10.1145/2983323.2983893

DO - 10.1145/2983323.2983893

M3 - Conference contribution

AN - SCOPUS:84996558218

VL - 24-28-October-2016

SP - 1997

EP - 2000

BT - CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management

PB - Association for Computing Machinery

T2 - 25th ACM International Conference on Information and Knowledge Management, CIKM 2016

Y2 - 24 October 2016 through 28 October 2016

ER -

Access to Document

10.1145/2983323.2983893