Unsupervised Domain Adaptation using Lexical Transformations and Label Injection for Twitter Data

TL;DR

This paper introduces a dataset-centric approach to unsupervised domain adaptation for Twitter data, using lexical transformations to improve POS tagging accuracy close to supervised levels.

Contribution

It proposes simple lexical transformations and label injection techniques to adapt source datasets for better performance on Twitter data without labeled target data.

Findings

Transformed datasets significantly improve POS tagging accuracy.

Achieved 92.14% POS tagging accuracy, close to supervised performance.

State-of-the-art results on Twitter POS tagging with synthetic data augmentation.

Abstract

Domain adaptation is an important and widely studied problem in natural language processing. A large body of literature tries to solve this problem by adapting models trained on the source domain to the target domain. In this paper, we instead solve this problem from a dataset perspective. We modify the source domain dataset with simple lexical transformations to reduce the domain shift between the source dataset distribution and the target dataset distribution. We find that models trained on the transformed source domain dataset performs significantly better than zero-shot models. Using our proposed transformations to convert standard English to tweets, we reach an unsupervised part-of-speech (POS) tagging accuracy of 92.14% (from 81.54% zero shot accuracy), which is only slightly below the supervised performance of 94.45%. We also use our proposed transformations to synthetically generate tweets and augment the Twitter dataset to achieve state-of-the-art performance for POS tagging.