Forskning ved Københavns Universitet - Københavns Universitet

Forside

Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Dokumenter

We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and auxiliary, annotated datasets. We evaluate our approach on a variety of tasks with disparate label spaces. We outperform strong single and multi-task baselines and achieve a new state of the art for aspect-based and topic-based sentiment analysis.
OriginalsprogEngelsk
TitelProceedings, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies : (Long Papers)
Antal sider11
Vol/bind1
ForlagAssociation for Computational Linguistics
Publikationsdato2018
Sider1896–1906
DOI
StatusUdgivet - 2018
Begivenhed16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - New Orleans, USA
Varighed: 1 jun. 20186 jun. 2018

Konference

Konference16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
LandUSA
ByNew Orleans
Periode01/06/201806/06/2018

Links

Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk


Ingen data tilgængelig

ID: 195047317