Macquarie University at BioASQ 6b: deep learning and deep reinforcement learning for query-based multi-document summarisation

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

Abstract

This paper describes Macquarie University’s contribution to the BioASQ Challenge (BioASQ 6b, Phase B). We focused on the extraction of the ideal answers, and the task was approached as an instance of query-based multi-document summarisation. In particular, this paper focuses on the experiments related to the deep learning and reinforcement learning approaches used in the submitted runs. The best run used a deep learning model under a regression-based framework. The deep learning architecture used features derived from the output of LSTM chains on word embeddings, plus features based on similarity with the query, and sentence position. The reinforcement learning approach was a proof-of-concept prototype that trained a global policy using REINFORCE. The global policy was implemented as a neural network that used tf.idf features encoding the candidate sentence, question, and context.
LanguageEnglish
Title of host publicationThe 6th BioASQ Workshop
Subtitle of host publicationA challenge on large-scale biomedical semantic indexing and question answering: Proceedings of the Workshop
Place of PublicationStroudsburg
PublisherAssociation for Computational Linguistics
Pages22-29
Number of pages8
ISBN (Electronic)9781948087704
Publication statusPublished - 2018
Event2018 Conference on Empirical Methods in Natural Language Processing (EMNLP) - Brussels, Belgium
Duration: 31 Oct 20184 Nov 2018

Conference

Conference2018 Conference on Empirical Methods in Natural Language Processing (EMNLP)
CountryBelgium
CityBrussels
Period31/10/184/11/18

Fingerprint

Reinforcement learning
Neural networks
Deep learning
Experiments

Cite this

Molla, D. (2018). Macquarie University at BioASQ 6b: deep learning and deep reinforcement learning for query-based multi-document summarisation. In The 6th BioASQ Workshop: A challenge on large-scale biomedical semantic indexing and question answering: Proceedings of the Workshop (pp. 22-29). Stroudsburg: Association for Computational Linguistics.
Molla, Diego. / Macquarie University at BioASQ 6b : deep learning and deep reinforcement learning for query-based multi-document summarisation. The 6th BioASQ Workshop: A challenge on large-scale biomedical semantic indexing and question answering: Proceedings of the Workshop. Stroudsburg : Association for Computational Linguistics, 2018. pp. 22-29
@inproceedings{dd34dd69ba734daf83250c2c90b81c62,
title = "Macquarie University at BioASQ 6b: deep learning and deep reinforcement learning for query-based multi-document summarisation",
abstract = "This paper describes Macquarie University’s contribution to the BioASQ Challenge (BioASQ 6b, Phase B). We focused on the extraction of the ideal answers, and the task was approached as an instance of query-based multi-document summarisation. In particular, this paper focuses on the experiments related to the deep learning and reinforcement learning approaches used in the submitted runs. The best run used a deep learning model under a regression-based framework. The deep learning architecture used features derived from the output of LSTM chains on word embeddings, plus features based on similarity with the query, and sentence position. The reinforcement learning approach was a proof-of-concept prototype that trained a global policy using REINFORCE. The global policy was implemented as a neural network that used tf.idf features encoding the candidate sentence, question, and context.",
author = "Diego Molla",
year = "2018",
language = "English",
pages = "22--29",
booktitle = "The 6th BioASQ Workshop",
publisher = "Association for Computational Linguistics",

}

Molla, D 2018, Macquarie University at BioASQ 6b: deep learning and deep reinforcement learning for query-based multi-document summarisation. in The 6th BioASQ Workshop: A challenge on large-scale biomedical semantic indexing and question answering: Proceedings of the Workshop. Association for Computational Linguistics, Stroudsburg, pp. 22-29, 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), Brussels, Belgium, 31/10/18.

Macquarie University at BioASQ 6b : deep learning and deep reinforcement learning for query-based multi-document summarisation. / Molla, Diego.

The 6th BioASQ Workshop: A challenge on large-scale biomedical semantic indexing and question answering: Proceedings of the Workshop. Stroudsburg : Association for Computational Linguistics, 2018. p. 22-29.

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

TY - GEN

T1 - Macquarie University at BioASQ 6b

T2 - deep learning and deep reinforcement learning for query-based multi-document summarisation

AU - Molla,Diego

PY - 2018

Y1 - 2018

N2 - This paper describes Macquarie University’s contribution to the BioASQ Challenge (BioASQ 6b, Phase B). We focused on the extraction of the ideal answers, and the task was approached as an instance of query-based multi-document summarisation. In particular, this paper focuses on the experiments related to the deep learning and reinforcement learning approaches used in the submitted runs. The best run used a deep learning model under a regression-based framework. The deep learning architecture used features derived from the output of LSTM chains on word embeddings, plus features based on similarity with the query, and sentence position. The reinforcement learning approach was a proof-of-concept prototype that trained a global policy using REINFORCE. The global policy was implemented as a neural network that used tf.idf features encoding the candidate sentence, question, and context.

AB - This paper describes Macquarie University’s contribution to the BioASQ Challenge (BioASQ 6b, Phase B). We focused on the extraction of the ideal answers, and the task was approached as an instance of query-based multi-document summarisation. In particular, this paper focuses on the experiments related to the deep learning and reinforcement learning approaches used in the submitted runs. The best run used a deep learning model under a regression-based framework. The deep learning architecture used features derived from the output of LSTM chains on word embeddings, plus features based on similarity with the query, and sentence position. The reinforcement learning approach was a proof-of-concept prototype that trained a global policy using REINFORCE. The global policy was implemented as a neural network that used tf.idf features encoding the candidate sentence, question, and context.

M3 - Conference proceeding contribution

SP - 22

EP - 29

BT - The 6th BioASQ Workshop

PB - Association for Computational Linguistics

CY - Stroudsburg

ER -

Molla D. Macquarie University at BioASQ 6b: deep learning and deep reinforcement learning for query-based multi-document summarisation. In The 6th BioASQ Workshop: A challenge on large-scale biomedical semantic indexing and question answering: Proceedings of the Workshop. Stroudsburg: Association for Computational Linguistics. 2018. p. 22-29