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

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › 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.

Originalsprog	Engelsk
Titel	Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics
Forlag	Association for Computational Linguistics
Publikationsdato	2017
Sider	230-240
ISBN (Elektronisk)	978-1-945626-34-0
Status	Udgivet - 2017
Begivenhed	The 15th Conference of the European Chapter of the Association for Computational Linguistics - Valencia, Spanien Varighed: 3 apr. 2017 → 7 apr. 2017 http://eacl2017.org/

Konference

Konference	The 15th Conference of the European Chapter of the Association for Computational Linguistics
Land/Område	Spanien
By	Valencia
Periode	03/04/2017 → 07/04/2017
Internetadresse	http://eacl2017.org/

Emneord

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

Adgang til dokumentet

alonso2017-parsing.preprintAccepteret manuskript, 301 KB

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

Citationsformater

@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, 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. i Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, s. 230-240, The 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spanien, 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. s. 230-240.

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › 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

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

Konference

Emneord

Adgang til dokumentet

Fingeraftryk

Citationsformater