An approach for query-focused text summarisation for evidence based medicine

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

Abstract

We present an approach for extractive, query-focused, single-document summarisation of medical text. Our approach utilises a combination of target-sentence-specific and target-sentence-independent statistics derived from a corpus specialised for summarisation in the medical domain. We incorporate domain knowledge via the application of multiple domain-specific features, and we customise the answer extraction process for different question types. The use of carefully selected domain-specific features enables our summariser to generate content-rich extractive summaries, and an automatic evaluation of our system reveals that it outperforms other baseline and benchmark summarisation systems with a percentile rank of 96.8%.

LanguageEnglish
Title of host publicationArtificial Intelligence in Medicine
Subtitle of host publication14th Conference on Artificial Intelligence in Medicine, AIME 2013, Murcia, Spain, May 29 – June 1, 2013. Proceedings
EditorsNiels Peek, Roque Marín Morales, Mor Peleg
Place of PublicationHeidelberg
PublisherSpringer, Springer Nature
Pages295-304
Number of pages10
ISBN (Electronic)9783642383267
ISBN (Print)9783642383250
DOIs
Publication statusPublished - 2013
Event14th Conference on Artificial Intelligence in Medicine, AIME 2013 - Murcia, Spain
Duration: 29 May 20131 Jun 2013

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
Volume7885
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Other

Other14th Conference on Artificial Intelligence in Medicine, AIME 2013
CountrySpain
CityMurcia
Period29/05/131/06/13

Fingerprint

Summarization
Medicine
Statistics
Query
Target
Percentile
Domain Knowledge
Baseline
Benchmark
Evaluation
Evidence
Text

Cite this

Sarker, A., Mollá, D., & Paris, C. (2013). An approach for query-focused text summarisation for evidence based medicine. In N. Peek, R. Marín Morales, & M. Peleg (Eds.), Artificial Intelligence in Medicine: 14th Conference on Artificial Intelligence in Medicine, AIME 2013, Murcia, Spain, May 29 – June 1, 2013. Proceedings (pp. 295-304). (Lecture Notes in Computer Science; Vol. 7885). Heidelberg: Springer, Springer Nature. https://doi.org/10.1007/978-3-642-38326-7_41
Sarker, Abeed ; Mollá, Diego ; Paris, Cécile. / An approach for query-focused text summarisation for evidence based medicine. Artificial Intelligence in Medicine: 14th Conference on Artificial Intelligence in Medicine, AIME 2013, Murcia, Spain, May 29 – June 1, 2013. Proceedings. editor / Niels Peek ; Roque Marín Morales ; Mor Peleg. Heidelberg : Springer, Springer Nature, 2013. pp. 295-304 (Lecture Notes in Computer Science).
@inproceedings{95ba2000b71c48c6a8e0aa0fb8375c34,
title = "An approach for query-focused text summarisation for evidence based medicine",
abstract = "We present an approach for extractive, query-focused, single-document summarisation of medical text. Our approach utilises a combination of target-sentence-specific and target-sentence-independent statistics derived from a corpus specialised for summarisation in the medical domain. We incorporate domain knowledge via the application of multiple domain-specific features, and we customise the answer extraction process for different question types. The use of carefully selected domain-specific features enables our summariser to generate content-rich extractive summaries, and an automatic evaluation of our system reveals that it outperforms other baseline and benchmark summarisation systems with a percentile rank of 96.8{\%}.",
author = "Abeed Sarker and Diego Moll{\'a} and C{\'e}cile Paris",
year = "2013",
doi = "10.1007/978-3-642-38326-7_41",
language = "English",
isbn = "9783642383250",
series = "Lecture Notes in Computer Science",
publisher = "Springer, Springer Nature",
pages = "295--304",
editor = "Niels Peek and {Mar{\'i}n Morales}, Roque and Mor Peleg",
booktitle = "Artificial Intelligence in Medicine",
address = "United States",

}

Sarker, A, Mollá, D & Paris, C 2013, An approach for query-focused text summarisation for evidence based medicine. in N Peek, R Marín Morales & M Peleg (eds), Artificial Intelligence in Medicine: 14th Conference on Artificial Intelligence in Medicine, AIME 2013, Murcia, Spain, May 29 – June 1, 2013. Proceedings. Lecture Notes in Computer Science, vol. 7885, Springer, Springer Nature, Heidelberg, pp. 295-304, 14th Conference on Artificial Intelligence in Medicine, AIME 2013, Murcia, Spain, 29/05/13. https://doi.org/10.1007/978-3-642-38326-7_41

An approach for query-focused text summarisation for evidence based medicine. / Sarker, Abeed; Mollá, Diego; Paris, Cécile.

Artificial Intelligence in Medicine: 14th Conference on Artificial Intelligence in Medicine, AIME 2013, Murcia, Spain, May 29 – June 1, 2013. Proceedings. ed. / Niels Peek; Roque Marín Morales; Mor Peleg. Heidelberg : Springer, Springer Nature, 2013. p. 295-304 (Lecture Notes in Computer Science; Vol. 7885).

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

TY - GEN

T1 - An approach for query-focused text summarisation for evidence based medicine

AU - Sarker, Abeed

AU - Mollá, Diego

AU - Paris, Cécile

PY - 2013

Y1 - 2013

N2 - We present an approach for extractive, query-focused, single-document summarisation of medical text. Our approach utilises a combination of target-sentence-specific and target-sentence-independent statistics derived from a corpus specialised for summarisation in the medical domain. We incorporate domain knowledge via the application of multiple domain-specific features, and we customise the answer extraction process for different question types. The use of carefully selected domain-specific features enables our summariser to generate content-rich extractive summaries, and an automatic evaluation of our system reveals that it outperforms other baseline and benchmark summarisation systems with a percentile rank of 96.8%.

AB - We present an approach for extractive, query-focused, single-document summarisation of medical text. Our approach utilises a combination of target-sentence-specific and target-sentence-independent statistics derived from a corpus specialised for summarisation in the medical domain. We incorporate domain knowledge via the application of multiple domain-specific features, and we customise the answer extraction process for different question types. The use of carefully selected domain-specific features enables our summariser to generate content-rich extractive summaries, and an automatic evaluation of our system reveals that it outperforms other baseline and benchmark summarisation systems with a percentile rank of 96.8%.

UR - http://www.scopus.com/inward/record.url?scp=84887297981&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-38326-7_41

DO - 10.1007/978-3-642-38326-7_41

M3 - Conference proceeding contribution

SN - 9783642383250

T3 - Lecture Notes in Computer Science

SP - 295

EP - 304

BT - Artificial Intelligence in Medicine

A2 - Peek, Niels

A2 - Marín Morales, Roque

A2 - Peleg, Mor

PB - Springer, Springer Nature

CY - Heidelberg

ER -

Sarker A, Mollá D, Paris C. An approach for query-focused text summarisation for evidence based medicine. In Peek N, Marín Morales R, Peleg M, editors, Artificial Intelligence in Medicine: 14th Conference on Artificial Intelligence in Medicine, AIME 2013, Murcia, Spain, May 29 – June 1, 2013. Proceedings. Heidelberg: Springer, Springer Nature. 2013. p. 295-304. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-642-38326-7_41