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

Basirat, A & Nivre, J 2020 'Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features'.

APA

Basirat, A., & Nivre, J. (2020). Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features.

Vancouver

Basirat A, Nivre J. Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features. 2020 Jul 9.

Author

Basirat, Ali ; Nivre, Joakim. / Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features. 2020.

Bibtex

@techreport{4eef0cbb74b941eeb4dd8259f72e3c51,
title = "Greedy Transition-Based Dependency Parsing with Discrete and Continuous Supertag Features",
abstract = " 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. ",
keywords = "cs.CL",
author = "Ali Basirat and Joakim Nivre",
note = "This paper was originally submitted to EMNLP 2015 and has not been previously published",
year = "2020",
month = jul,
day = "9",
language = "Udefineret/Ukendt",
type = "WorkingPaper",

}

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