Cui, Xia ORCID: 0000-0002-1726-3814 and Bollegala, Danushka
(2020)
Multi-source Attention for Unsupervised Domain Adaptation.
CoRR, abs/20.
Text
2004.06608v2.pdf - Submitted version Download (791kB) | Preview |
Abstract
Domain adaptation considers the problem of generalising a model learnt using data from a particular source domain to a different target domain. Often it is difficult to find a suitable single source to adapt from, and one must consider multiple sources. Using an unrelated source can result in sub-optimal performance, known as the \emph{negative transfer}. However, it is challenging to select the appropriate source(s) for classifying a given target instance in multi-source unsupervised domain adaptation (UDA). We model source-selection as an attention-learning problem, where we learn attention over sources for a given target instance. For this purpose, we first independently learn source-specific classification models, and a relatedness map between sources and target domains using pseudo-labelled target domain instances. Next, we learn attention-weights over the sources for aggregating the predictions of the source-specific models. Experimental results on cross-domain sentiment classification benchmarks show that the proposed method outperforms prior proposals in multi-source UDA.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | cs.CL, cs.CL, cs.LG |
Depositing User: | Symplectic Admin |
Date Deposited: | 30 Apr 2020 10:37 |
Last Modified: | 18 Jan 2023 23:53 |
Related URLs: | |
URI: | https://livrepository.liverpool.ac.uk/id/eprint/3085261 |