Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces
Computation and Language
2018-04-10 v2 Neural and Evolutionary Computing
Machine Learning
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.
Cite
@article{arxiv.1802.09913,
title = {Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces},
author = {Isabelle Augenstein and Sebastian Ruder and Anders Søgaard},
journal= {arXiv preprint arXiv:1802.09913},
year = {2018}
}
Comments
To appear at NAACL 2018 (long)