Show simple item record

dc.contributor.authorKochkina, E
dc.contributor.authorLiakata, M
dc.contributor.authorZUBIAGA, A
dc.contributor.authorInternational Conference on Computational Linguistics
dc.date.accessioned2019-03-22T11:43:01Z
dc.date.available2018-05-16
dc.date.available2019-03-22T11:43:01Z
dc.date.issued2018
dc.identifier.citationKochkina, E., Liakata, M. and Zubiaga, A. (2019). All-in-one: Multi-task Learning for Rumour Verification. [online] arXiv.org. Available at: https://arxiv.org/abs/1806.03713 [Accessed 22 Mar. 2019].en_US
dc.identifier.urihttps://qmro.qmul.ac.uk/xmlui/handle/123456789/56424
dc.description.abstractAutomatic resolution of rumours is a challenging task that can be broken down into smaller components that make up a pipeline, including rumour detection, rumour tracking and stance classification, leading to the final outcome of determining the veracity of a rumour. In previous work, these steps in the process of rumour verification have been developed as separate components where the output of one feeds into the next. We propose a multi-task learning approach that allows joint training of the main and auxiliary tasks, improving the performance of rumour verification. We examine the connection between the dataset properties and the outcomes of the multi-task learning models used.en_US
dc.format.extent3402 - 3413 (12)
dc.publisherAssociation for Computational Linguisticsen_US
dc.titleAll-in-one: Multi-task Learning for Rumour Verificationen_US
dc.typeConference Proceedingen_US
dc.rights.holder© The Author(s) 2018
pubs.notesNo embargoen_US
pubs.publication-statusPublisheden_US
dcterms.dateAccepted2018-05-16
rioxxterms.funderDefault funderen_US
rioxxterms.identifier.projectDefault projecten_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record