Joint POS Tagging and Dependency Parsing with Transition-based Neural Networks
This work addresses feature sparsity and incompleteness in joint modeling for NLP tasks, representing an incremental improvement over existing methods.
The paper tackled the problem of joint POS tagging and dependency parsing by proposing a transition-based neural network approach, which significantly outperformed previous methods across multiple natural languages.
While part-of-speech (POS) tagging and dependency parsing are observed to be closely related, existing work on joint modeling with manually crafted feature templates suffers from the feature sparsity and incompleteness problems. In this paper, we propose an approach to joint POS tagging and dependency parsing using transition-based neural networks. Three neural network based classifiers are designed to resolve shift/reduce, tagging, and labeling conflicts. Experiments show that our approach significantly outperforms previous methods for joint POS tagging and dependency parsing across a variety of natural languages.