Deep Contextualized Self-training for Low Resource Dependency Parsing
This addresses the annotation bottleneck for low-resource dependency parsing, making it more accessible for domains and languages with limited labeled data, though it is incremental as it builds on existing self-training methods.
The paper tackles the problem of dependency parsing requiring large labeled datasets by proposing a self-training algorithm that trains a parser on its own output, resulting in substantial performance improvements over traditional self-training and recent semi-supervised methods across multiple languages and setups.
Neural dependency parsing has proven very effective, achieving state-of-the-art results on numerous domains and languages. Unfortunately, it requires large amounts of labeled data, that is costly and laborious to create. In this paper we propose a self-training algorithm that alleviates this annotation bottleneck by training a parser on its own output. Our Deep Contextualized Self-training (DCST) algorithm utilizes representation models trained on sequence labeling tasks that are derived from the parser's output when applied to unlabeled data, and integrates these models with the base parser through a gating mechanism. We conduct experiments across multiple languages, both in low resource in-domain and in cross-domain setups, and demonstrate that DCST substantially outperforms traditional self-training as well as recent semi-supervised training methods.