Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features
Research output: Working paper › Preprint › Research
Standard
Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features. / Basirat, Ali; Nivre, Joakim.
2020.Research output: Working paper › Preprint › Research
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - UNPB
T1 - Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features
AU - Basirat, Ali
AU - Nivre, Joakim
N1 - This paper was originally submitted to EMNLP 2015 and has not been previously published
PY - 2020/7/9
Y1 - 2020/7/9
N2 - 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.
AB - 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.
KW - cs.CL
M3 - Preprint
BT - Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features
ER -
ID: 366049023