Bidirectional Domain Adaptation Using Weighted Multi-Task Learning

Abstract

Domain adaption in syntactic parsing is still a significant challenge. We address the issue of data imbalance between the in-domain and out-of-domain treebank typically used for the problem. We define domain adaptation as a Multi-task learning (MTL) problem, which allows us to train two parsers, one for each domain. Our results show that the MTL approach is beneficial for the smaller treebank. For the larger treebank, we need to use loss weighting in order to avoid a decrease in performance below the single task. In order to determine to what degree the data imbalance between two domains and the domain differences affect results, we also carry out an experiment with two imbalanced in-domain treebanks and show that loss weighting also improves performance in an in-domain setting. Given loss weighting in MTL, we can improve results for both parsers.

Semi-supervised Domain Adaptation for Dependency Parsing with Dynamic Matching Network

“…In the past few years, semi-supervised dependency parsing has attracted more attention with the surge of labeled web data that are user-generated non-canonical texts (Yu et al, 2013;Peng et al, 2019;Li et al, 2019b;Dakota et al, 2021). As shown in Figure 2, these approaches for modeling the similarity and discrepancy among different domains can be classified into three categories.…”