Multiple-Source Domain Adaptation via Coordinated Domain Encoders and Paired Classifiers

TL;DR

This paper introduces a novel multiple-source unsupervised domain adaptation model for text classification that dynamically integrates domain encoders and pairs classifiers based on a probabilistic heuristic, outperforming existing methods.

Contribution

The paper proposes a new approach combining dynamic domain encoder integration and probabilistic classifier pairing for improved unsupervised domain adaptation in text classification.

Findings

Our model outperforms existing domain adaptation methods.

Pretrained transformers can be effectively integrated into the adaptation framework.

The heuristic accurately infers target domain error rates.

Abstract

We present a novel multiple-source unsupervised model for text classification under domain shift. Our model exploits the update rates in document representations to dynamically integrate domain encoders. It also employs a probabilistic heuristic to infer the error rate in the target domain in order to pair source classifiers. Our heuristic exploits data transformation cost and the classifier accuracy in the target feature space. We have used real world scenarios of Domain Adaptation to evaluate the efficacy of our algorithm. We also used pretrained multi-layer transformers as the document encoder in the experiments to demonstrate whether the improvement achieved by domain adaptation models can be delivered by out-of-the-box language model pretraining. The experiments testify that our model is the top performing approach in this setting.