Tri-Training

Supervised learning has been recently used to improve the performance of word alignment. However, due to the limited amount of labeled data, the performance of ”pure” supervised learning, which only …...

This paper proposes a simple yet effective framework for semi-supervised dependency parsing at entire tree level, referred to as ambiguity-aware ensemble training. Instead of only using 1- best parse trees …...

AbstractLack of labelled data in the target domain for training is a common problem in domain adaptation. To overcome this problem, we propose a novel unsupervised domain adaptation method that …...

AbstractWe compare two orthogonal semi-supervised learning techniques, namely tri-training and pretrained word embeddings, in the task of dependency parsing. We explore language-specific FastText and ELMo embeddings and multilingual BERT embeddings. …...

AbstractDiscourse parsing has been studied for decades. However, it still remains challenging to utilize discourse parsing for real-world applications because the parsing accuracy degrades significantly on out-of-domain text. In this …...