Classification betters regression in query-based multi-document summarisation techniques for question answering: Macquarie University at BioASQ7b

Diego Mollá; Christopher Jones

doi:10.1007/978-3-030-43887-6_56

Classification betters regression in query-based multi-document summarisation techniques for question answering: Macquarie University at BioASQ7b

Diego Mollá^*, Christopher Jones

^*Corresponding author for this work

School of Computing

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

6 Citations (Scopus)

Abstract

Task B Phase B of the 2019 BioASQ challenge focuses on biomedical question answering. Macquarie University’s participation applies query-based multi-document extractive summarisation techniques to generate a multi-sentence answer given the question and the set of relevant snippets. In past participation we explored the use of regression approaches using deep learning architectures and a simple policy gradient architecture. For the 2019 challenge we experiment with the use of classification approaches with and without reinforcement learning. In addition, we conduct a correlation analysis between various ROUGE metrics and the BioASQ human evaluation scores.

Original language	English
Title of host publication	Machine Learning and Knowledge Discovery in Databases
Subtitle of host publication	International Workshops of ECML PKDD 2019, Proceedings
Editors	Peggy Cellier, Kurt Driessens
Place of Publication	Cham, Switzerland
Publisher	Springer, Springer Nature
Pages	624-635
Number of pages	12
ISBN (Electronic)	9783030438876
ISBN (Print)	9783030438869
DOIs	https://doi.org/10.1007/978-3-030-43887-6_56
Publication status	Published - 2020
Event	19th Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2019 - Wurzburg, Germany Duration: 16 Sept 2019 → 20 Sept 2019

Publication series

Name	Communications in Computer and Information Science
Volume	1168 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	19th Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2019
Country/Territory	Germany
City	Wurzburg
Period	16/09/19 → 20/09/19

Keywords

Deep learning
Evaluation
Query-based summarisation
Reinforcement learning

Access to Document

10.1007/978-3-030-43887-6_56

Cite this

Mollá, D., & Jones, C. (2020). Classification betters regression in query-based multi-document summarisation techniques for question answering: Macquarie University at BioASQ7b. In P. Cellier, & K. Driessens (Eds.), Machine Learning and Knowledge Discovery in Databases: International Workshops of ECML PKDD 2019, Proceedings (pp. 624-635). (Communications in Computer and Information Science; Vol. 1168 CCIS). Springer, Springer Nature. https://doi.org/10.1007/978-3-030-43887-6_56

Mollá, Diego ; Jones, Christopher. / Classification betters regression in query-based multi-document summarisation techniques for question answering : Macquarie University at BioASQ7b. Machine Learning and Knowledge Discovery in Databases: International Workshops of ECML PKDD 2019, Proceedings. editor / Peggy Cellier ; Kurt Driessens. Cham, Switzerland : Springer, Springer Nature, 2020. pp. 624-635 (Communications in Computer and Information Science).

@inproceedings{bd5b226c176e44db839e0fce50dff3c0,

title = "Classification betters regression in query-based multi-document summarisation techniques for question answering: Macquarie University at BioASQ7b",

abstract = "Task B Phase B of the 2019 BioASQ challenge focuses on biomedical question answering. Macquarie University{\textquoteright}s participation applies query-based multi-document extractive summarisation techniques to generate a multi-sentence answer given the question and the set of relevant snippets. In past participation we explored the use of regression approaches using deep learning architectures and a simple policy gradient architecture. For the 2019 challenge we experiment with the use of classification approaches with and without reinforcement learning. In addition, we conduct a correlation analysis between various ROUGE metrics and the BioASQ human evaluation scores.",

keywords = "Deep learning, Evaluation, Query-based summarisation, Reinforcement learning",

author = "Diego Moll{\'a} and Christopher Jones",

year = "2020",

doi = "10.1007/978-3-030-43887-6_56",

language = "English",

isbn = "9783030438869",

series = "Communications in Computer and Information Science",

publisher = "Springer, Springer Nature",

pages = "624--635",

editor = "Peggy Cellier and Kurt Driessens",

booktitle = "Machine Learning and Knowledge Discovery in Databases",

address = "United States",

note = "19th Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2019 ; Conference date: 16-09-2019 Through 20-09-2019",

}

Mollá, D & Jones, C 2020, Classification betters regression in query-based multi-document summarisation techniques for question answering: Macquarie University at BioASQ7b. in P Cellier & K Driessens (eds), Machine Learning and Knowledge Discovery in Databases: International Workshops of ECML PKDD 2019, Proceedings. Communications in Computer and Information Science, vol. 1168 CCIS, Springer, Springer Nature, Cham, Switzerland, pp. 624-635, 19th Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2019, Wurzburg, Germany, 16/09/19. https://doi.org/10.1007/978-3-030-43887-6_56

Classification betters regression in query-based multi-document summarisation techniques for question answering: Macquarie University at BioASQ7b. / Mollá, Diego; Jones, Christopher.
Machine Learning and Knowledge Discovery in Databases: International Workshops of ECML PKDD 2019, Proceedings. ed. / Peggy Cellier; Kurt Driessens. Cham, Switzerland: Springer, Springer Nature, 2020. p. 624-635 (Communications in Computer and Information Science; Vol. 1168 CCIS).

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

TY - GEN

T1 - Classification betters regression in query-based multi-document summarisation techniques for question answering

T2 - 19th Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2019

AU - Mollá, Diego

AU - Jones, Christopher

PY - 2020

Y1 - 2020

N2 - Task B Phase B of the 2019 BioASQ challenge focuses on biomedical question answering. Macquarie University’s participation applies query-based multi-document extractive summarisation techniques to generate a multi-sentence answer given the question and the set of relevant snippets. In past participation we explored the use of regression approaches using deep learning architectures and a simple policy gradient architecture. For the 2019 challenge we experiment with the use of classification approaches with and without reinforcement learning. In addition, we conduct a correlation analysis between various ROUGE metrics and the BioASQ human evaluation scores.

AB - Task B Phase B of the 2019 BioASQ challenge focuses on biomedical question answering. Macquarie University’s participation applies query-based multi-document extractive summarisation techniques to generate a multi-sentence answer given the question and the set of relevant snippets. In past participation we explored the use of regression approaches using deep learning architectures and a simple policy gradient architecture. For the 2019 challenge we experiment with the use of classification approaches with and without reinforcement learning. In addition, we conduct a correlation analysis between various ROUGE metrics and the BioASQ human evaluation scores.

KW - Deep learning

KW - Evaluation

KW - Query-based summarisation

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=85083670797&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-43887-6_56

DO - 10.1007/978-3-030-43887-6_56

M3 - Conference proceeding contribution

AN - SCOPUS:85083670797

SN - 9783030438869

T3 - Communications in Computer and Information Science

SP - 624

EP - 635

BT - Machine Learning and Knowledge Discovery in Databases

A2 - Cellier, Peggy

A2 - Driessens, Kurt

PB - Springer, Springer Nature

CY - Cham, Switzerland

Y2 - 16 September 2019 through 20 September 2019

ER -

Mollá D, Jones C. Classification betters regression in query-based multi-document summarisation techniques for question answering: Macquarie University at BioASQ7b. In Cellier P, Driessens K, editors, Machine Learning and Knowledge Discovery in Databases: International Workshops of ECML PKDD 2019, Proceedings. Cham, Switzerland: Springer, Springer Nature. 2020. p. 624-635. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-43887-6_56

Classification betters regression in query-based multi-document summarisation techniques for question answering: Macquarie University at BioASQ7b

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this