Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features
Publikation: Working paper › Preprint › Forskning
Dokumenter
- 2007.04686v1
193 KB, PDF-dokument
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.
Originalsprog | Udefineret/Ukendt |
---|---|
Status | Udgivet - 9 jul. 2020 |
Eksternt udgivet | Ja |
- cs.CL
Forskningsområder
ID: 366049023