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

ACL 2018

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

Jan 21, 2021
|
52 views
|
Details
Abstract: 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 sequence classification tasks with disparate label spaces. We outperform strong single and multi-task baselines and achieve a new state-of-the-art for topic-based sentiment analysis. Authors: Isabelle Augenstein, Sebastian Ruder, Anders Søgaard (National University of Ireland, University of Copenhagen, Aylien Ltd)

Comments
loading...