Parsing Universal Dependencies without training

Hector Martinez Alonso; Zeljko Agic; Barbara  Plank; Anders Søgaard

Parsing Universal Dependencies without training

Hector Martinez Alonso, Zeljko Agic, Barbara Plank, Anders Søgaard

Department of Computer Science

7 Citations (Scopus)

Abstract

We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It features two-step decoding to guarantee that function words are attached as leaf nodes. The parser requires no training, and it is competitive with a delexicalized transfer system. UDP offers a linguistically sound unsupervised alternative to cross-lingual parsing for UD, which can be used as a baseline for such systems. The parser has very few parameters and is distinctly robust to domain change across languages.

Original language	English
Title of host publication	Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics : long papers
Number of pages	11
Volume	1
Publisher	Association for Computational Linguistics
Publication date	2017
Pages	230-240
ISBN (Electronic)	978-1-945626-34-0
Publication status	Published - 2017
Event	15th Conference of the European Chapter of the Association for Computational Linguistics - Valencia, Spain Duration: 3 Apr 2017 → 7 Apr 2017 Conference number: 15

Conference

Conference	15th Conference of the European Chapter of the Association for Computational Linguistics
Number	15
Country/Territory	Spain
City	Valencia
Period	03/04/2017 → 07/04/2017

Access to Document

http://www.aclweb.org/anthology/E17-1022

Cite this

Parsing Universal Dependencies without training. / Martinez Alonso, Hector; Agic, Zeljko; Plank, Barbara et al.
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: long papers. Vol. 1 Association for Computational Linguistics, 2017. p. 230-240.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Martinez Alonso, H, Agic, Z, Plank, B & Søgaard, A 2017, Parsing Universal Dependencies without training. in Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: long papers. vol. 1, Association for Computational Linguistics, pp. 230-240, 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain, 03/04/2017. <http://www.aclweb.org/anthology/E17-1022>

@inproceedings{7c52451ba7914c869bce87ead08de76f,

title = "Parsing Universal Dependencies without training",

abstract = "We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It features two-step decoding to guarantee that function words are attached as leaf nodes. The parser requires no training, and it is competitive with a delexicalized transfer system. UDP offers a linguistically sound unsupervised alternative to cross-lingual parsing for UD, which can be used as a baseline for such systems. The parser has very few parameters and is distinctly robust to domain change across languages.",

author = "{Martinez Alonso}, Hector and Zeljko Agic and Barbara Plank and Anders S{\o}gaard",

year = "2017",

language = "English",

volume = "1",

pages = "230--240",

booktitle = "Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

note = "15th Conference of the European Chapter of the Association for Computational Linguistics ; Conference date: 03-04-2017 Through 07-04-2017",

}

TY - GEN

T1 - Parsing Universal Dependencies without training

AU - Martinez Alonso, Hector

AU - Agic, Zeljko

AU - Plank, Barbara

AU - Søgaard, Anders

N1 - Conference code: 15

PY - 2017

Y1 - 2017

N2 - We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It features two-step decoding to guarantee that function words are attached as leaf nodes. The parser requires no training, and it is competitive with a delexicalized transfer system. UDP offers a linguistically sound unsupervised alternative to cross-lingual parsing for UD, which can be used as a baseline for such systems. The parser has very few parameters and is distinctly robust to domain change across languages.

AB - We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It features two-step decoding to guarantee that function words are attached as leaf nodes. The parser requires no training, and it is competitive with a delexicalized transfer system. UDP offers a linguistically sound unsupervised alternative to cross-lingual parsing for UD, which can be used as a baseline for such systems. The parser has very few parameters and is distinctly robust to domain change across languages.

M3 - Article in proceedings

VL - 1

SP - 230

EP - 240

BT - Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics

PB - Association for Computational Linguistics

T2 - 15th Conference of the European Chapter of the Association for Computational Linguistics

Y2 - 3 April 2017 through 7 April 2017

ER -

Parsing Universal Dependencies without training

Abstract

Conference

Access to Document

Fingerprint

Cite this