SiS at CLEF 2017 eHealth tar task

Vassil Kalphov, Georgios Georgiadis, Leif Azzopardi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents Strathclyde iSchool's (SiS) participation in the Technological Assisted Reviews in Empirical Medicine Task. For the ranking task, we explored two ways in which assistance to reviewers could be provided during the assessment process: (i) topic models, where we use Latent Dirichlet Allocation to identify topics within the set of retrieved documents, ranking documents by the topic most likely to be relevant and (ii) relevance feedback, where we use Rocchio's algorithm to update the query model for subsequent rounds of interaction. A third approach combines the topic and relevance feedback to quickly identify the relevant abstracts. For the thresholding task, we apply a score threshold, and exclude documents which did not exceed the threshold given BM25.

LanguageEnglish
Pages1-5
Number of pages5
JournalCEUR Workshop Proceedings
Volume1866
Publication statusPublished - 11 Sep 2017

Fingerprint

Tar
Feedback
Medicine

Keywords

  • Technological Assisted Reviews in Empirical Medicine Task
  • TAR
  • relevance feedback
  • information retrieval

Cite this

Kalphov, V., Georgiadis, G., & Azzopardi, L. (2017). SiS at CLEF 2017 eHealth tar task. CEUR Workshop Proceedings, 1866, 1-5.
Kalphov, Vassil ; Georgiadis, Georgios ; Azzopardi, Leif. / SiS at CLEF 2017 eHealth tar task. In: CEUR Workshop Proceedings. 2017 ; Vol. 1866. pp. 1-5.
@article{221c1c700da743c2be5ea8f214121997,
title = "SiS at CLEF 2017 eHealth tar task",
abstract = "This paper presents Strathclyde iSchool's (SiS) participation in the Technological Assisted Reviews in Empirical Medicine Task. For the ranking task, we explored two ways in which assistance to reviewers could be provided during the assessment process: (i) topic models, where we use Latent Dirichlet Allocation to identify topics within the set of retrieved documents, ranking documents by the topic most likely to be relevant and (ii) relevance feedback, where we use Rocchio's algorithm to update the query model for subsequent rounds of interaction. A third approach combines the topic and relevance feedback to quickly identify the relevant abstracts. For the thresholding task, we apply a score threshold, and exclude documents which did not exceed the threshold given BM25.",
keywords = "Technological Assisted Reviews in Empirical Medicine Task, TAR, relevance feedback, information retrieval",
author = "Vassil Kalphov and Georgios Georgiadis and Leif Azzopardi",
year = "2017",
month = "9",
day = "11",
language = "English",
volume = "1866",
pages = "1--5",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",

}

Kalphov, V, Georgiadis, G & Azzopardi, L 2017, 'SiS at CLEF 2017 eHealth tar task' CEUR Workshop Proceedings, vol. 1866, pp. 1-5.

SiS at CLEF 2017 eHealth tar task. / Kalphov, Vassil; Georgiadis, Georgios; Azzopardi, Leif.

In: CEUR Workshop Proceedings, Vol. 1866, 11.09.2017, p. 1-5.

Research output: Contribution to journalArticle

TY - JOUR

T1 - SiS at CLEF 2017 eHealth tar task

AU - Kalphov, Vassil

AU - Georgiadis, Georgios

AU - Azzopardi, Leif

PY - 2017/9/11

Y1 - 2017/9/11

N2 - This paper presents Strathclyde iSchool's (SiS) participation in the Technological Assisted Reviews in Empirical Medicine Task. For the ranking task, we explored two ways in which assistance to reviewers could be provided during the assessment process: (i) topic models, where we use Latent Dirichlet Allocation to identify topics within the set of retrieved documents, ranking documents by the topic most likely to be relevant and (ii) relevance feedback, where we use Rocchio's algorithm to update the query model for subsequent rounds of interaction. A third approach combines the topic and relevance feedback to quickly identify the relevant abstracts. For the thresholding task, we apply a score threshold, and exclude documents which did not exceed the threshold given BM25.

AB - This paper presents Strathclyde iSchool's (SiS) participation in the Technological Assisted Reviews in Empirical Medicine Task. For the ranking task, we explored two ways in which assistance to reviewers could be provided during the assessment process: (i) topic models, where we use Latent Dirichlet Allocation to identify topics within the set of retrieved documents, ranking documents by the topic most likely to be relevant and (ii) relevance feedback, where we use Rocchio's algorithm to update the query model for subsequent rounds of interaction. A third approach combines the topic and relevance feedback to quickly identify the relevant abstracts. For the thresholding task, we apply a score threshold, and exclude documents which did not exceed the threshold given BM25.

KW - Technological Assisted Reviews in Empirical Medicine Task

KW - TAR

KW - relevance feedback

KW - information retrieval

UR - http://www.scopus.com/inward/record.url?scp=85034758813&partnerID=8YFLogxK

UR - http://ceur-ws.org/Vol-1866/

M3 - Article

VL - 1866

SP - 1

EP - 5

JO - CEUR Workshop Proceedings

T2 - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -

Kalphov V, Georgiadis G, Azzopardi L. SiS at CLEF 2017 eHealth tar task. CEUR Workshop Proceedings. 2017 Sep 11;1866:1-5.