Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features
This work addresses parsing accuracy for NLP researchers, offering an incremental enhancement over prior methods using supertag features.
The paper tackled improving greedy transition-based dependency parsing by incorporating both discrete and continuous supertag features, achieving state-of-the-art results with 88.6% LAS and 90.9% UAS on the English Penn Treebank.
We study the effect of rich supertag features in greedy transition-based dependency parsing. While previous studies have shown that sparse boolean features representing the 1-best supertag of a word can improve parsing accuracy, we show that we can get further improvements by adding a continuous vector representation of the entire supertag distribution for a word. In this way, we achieve the best results for greedy transition-based parsing with supertag features with $88.6\%$ LAS and $90.9\%$ UASon the English Penn Treebank converted to Stanford Dependencies.