Parsing Universal Dependencies without training

Héctor  Martínez Alonso; Zeljko Agic; Barbara Plank; Anders Søgaard

Parsing Universal Dependencies without training

Héctor Martínez Alonso, Zeljko Agic, Barbara Plank, Anders Søgaard

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

We present UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of specific dependency head rules. UDP 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. The parser has very few parameters and 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
Publisher	Association for Computational Linguistics
Publication date	2017
Pages	230-240
ISBN (Electronic)	978-1-945626-34-0
Publication status	Published - 2017
Event	The 15th Conference of the European Chapter of the Association for Computational Linguistics - Valencia, Spain Duration: 3 Apr 2017 → 7 Apr 2017 http://eacl2017.org/

Conference

Conference	The 15th Conference of the European Chapter of the Association for Computational Linguistics
Country/Territory	Spain
City	Valencia
Period	03/04/2017 → 07/04/2017
Internet address	http://eacl2017.org/

Keywords

Universal Dependencies
Training-free parsing
PageRank
Dependency head rules
Cross-lingual parsing

Access to Document

alonso2017-parsing.preprintAccepted author manuscript, 301 KB

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

Cite this

@inproceedings{8804f2e169564dc4a8731fef7583c294,

title = "Parsing Universal Dependencies without training",

abstract = "We present UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of specific dependency head rules. UDP 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. The parser has very few parameters and distinctly robust to domain change across languages.",

keywords = "Universal Dependencies, Training-free parsing, PageRank, Dependency head rules, Cross-lingual parsing",

author = "{Mart{\'i}nez Alonso}, H{\'e}ctor and Zeljko Agic and Barbara Plank and Anders S{\o}gaard",

year = "2017",

language = "English",

pages = "230--240",

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

publisher = "Association for Computational Linguistics",

address = "United States",

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

url = "http://eacl2017.org/",

}

Martínez 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. Association for Computational Linguistics, pp. 230-240, The 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain, 03/04/2017. <http://www.aclweb.org/anthology/E17-1022>

Parsing Universal Dependencies without training. / Martínez Alonso, Héctor ; Agic, Zeljko; Plank, Barbara et al.
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, 2017. p. 230-240.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

TY - GEN

T1 - Parsing Universal Dependencies without training

AU - Martínez Alonso, Héctor

AU - Agic, Zeljko

AU - Plank, Barbara

AU - Søgaard, Anders

PY - 2017

Y1 - 2017

N2 - We present UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of specific dependency head rules. UDP 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. The parser has very few parameters and distinctly robust to domain change across languages.

AB - We present UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of specific dependency head rules. UDP 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. The parser has very few parameters and distinctly robust to domain change across languages.

KW - Universal Dependencies

KW - Training-free parsing

KW - PageRank

KW - Dependency head rules

KW - Cross-lingual parsing

M3 - Article in proceedings

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 - The 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

Keywords

Access to Document

Fingerprint

Cite this