Iterative learning to rank from explicit relevance feedback

Mateus Pereira; Elham Etemad; Fernando V. Paulovich

doi:10.1145/3341105.3374002

Iterative learning to rank from explicit relevance feedback

Mateus Pereira
, Elham Etemad
, Fernando V. Paulovich

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

8 Citations (Scopus)

Abstract

Interactive information retrieval (IIR) models consider the implicit or explicit user feedback in order to understand their intent and improve the quality of retrieved documents. We are proposing an IIR model that combines explicit relevance feedback and learning to rank techniques to improve the quality of retrieved documents. Besides evaluating the proposed method in general information retrieval cases using LETOR datasets, we have applied it to the special case of Community Question Answering (CQA) systems using SemEval challenge data. The proposed method outperforms other existing learning to rank techniques on most of these datasets.

Original language	English
Title of host publication	SAC '20
Subtitle of host publication	Proceedings of the 35th Annual ACM Symposium on Applied Computing
Publisher	Association for Computing Machinery, Inc.
Pages	698-705
Number of pages	8
ISBN (Electronic)	9781450368667
DOIs	https://doi.org/10.1145/3341105.3374002
Publication status	Published - 30 Mar 2020
Externally published	Yes

Keywords

Community question answering
Explicit relevance feedback
Interactive learning to rank

Access to Document

10.1145/3341105.3374002

Cite this

@inproceedings{5f9eb02f215f49c0af2db8af6b184213,

title = "Iterative learning to rank from explicit relevance feedback",

abstract = "Interactive information retrieval (IIR) models consider the implicit or explicit user feedback in order to understand their intent and improve the quality of retrieved documents. We are proposing an IIR model that combines explicit relevance feedback and learning to rank techniques to improve the quality of retrieved documents. Besides evaluating the proposed method in general information retrieval cases using LETOR datasets, we have applied it to the special case of Community Question Answering (CQA) systems using SemEval challenge data. The proposed method outperforms other existing learning to rank techniques on most of these datasets.",

keywords = "Community question answering, Explicit relevance feedback, Interactive learning to rank",

author = "Mateus Pereira and Elham Etemad and Paulovich, \{Fernando V.\}",

year = "2020",

month = mar,

day = "30",

doi = "10.1145/3341105.3374002",

language = "English",

pages = "698--705",

booktitle = "SAC '20",

publisher = "Association for Computing Machinery, Inc.",

address = "United States",

}

Iterative learning to rank from explicit relevance feedback. / Pereira, Mateus; Etemad, Elham; Paulovich, Fernando V.
SAC '20: Proceedings of the 35th Annual ACM Symposium on Applied Computing. Association for Computing Machinery, Inc., 2020. p. 698-705.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Iterative learning to rank from explicit relevance feedback

AU - Pereira, Mateus

AU - Etemad, Elham

AU - Paulovich, Fernando V.

PY - 2020/3/30

Y1 - 2020/3/30

N2 - Interactive information retrieval (IIR) models consider the implicit or explicit user feedback in order to understand their intent and improve the quality of retrieved documents. We are proposing an IIR model that combines explicit relevance feedback and learning to rank techniques to improve the quality of retrieved documents. Besides evaluating the proposed method in general information retrieval cases using LETOR datasets, we have applied it to the special case of Community Question Answering (CQA) systems using SemEval challenge data. The proposed method outperforms other existing learning to rank techniques on most of these datasets.

AB - Interactive information retrieval (IIR) models consider the implicit or explicit user feedback in order to understand their intent and improve the quality of retrieved documents. We are proposing an IIR model that combines explicit relevance feedback and learning to rank techniques to improve the quality of retrieved documents. Besides evaluating the proposed method in general information retrieval cases using LETOR datasets, we have applied it to the special case of Community Question Answering (CQA) systems using SemEval challenge data. The proposed method outperforms other existing learning to rank techniques on most of these datasets.

KW - Community question answering

KW - Explicit relevance feedback

KW - Interactive learning to rank

UR - https://www.scopus.com/pages/publications/85083036273

U2 - 10.1145/3341105.3374002

DO - 10.1145/3341105.3374002

M3 - Conference contribution

SP - 698

EP - 705

BT - SAC '20

PB - Association for Computing Machinery, Inc.

ER -

Iterative learning to rank from explicit relevance feedback

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this