Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features
Research output: Working paper › Preprint › Research
Documents
- 2007.04686v1
193 KB, PDF document
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.
Original language | Undefined/Unknown |
---|---|
Publication status | Published - 9 Jul 2020 |
Externally published | Yes |
Bibliographical note
This paper was originally submitted to EMNLP 2015 and has not been previously published
ID: 366049023