A Dependency Parser for Tweets

Lingpeng Kong; Nathan Schneider; Swabha Swayamdipta; Archna Bhatia; Chris Dyer; Noah A. Smith

A Dependency Parser for Tweets

Lingpeng Kong, Nathan Schneider, Swabha Swayamdipta, Archna Bhatia, Chris Dyer, Noah A. Smith

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We describe a new dependency parser for English tweets, TWEEBOPARSER. The parser builds on several contributions: new syntactic annotations for a corpus of tweets (TWEEBANK), with conventions informed by the domain; adaptations to a statistical parsing algorithm; and a new approach to exploiting out-of-domain Penn Treebank data. Our experiments show that the parser achieves over 80% unlabeled attachment accuracy on our new, high-quality test set and measure the benefit of our contributions.Our dataset and parser can be found at http://www.ark.cs.cmu.edu/TweetNLP.

Original language	English
Title of host publication	Proceedings of the Conference on Empirical Methods in Natural Language Processing
Place of Publication	Doha, Qatar
Publisher	Association for Computational Linguistics
Pages	1001-1012
Number of pages	12
Publication status	Published - 1 Oct 2014

Access to Document

twparserFinal published version, 402 KB

http://www.aclweb.org/anthology/D14-1108

Cite this

@inproceedings{d25fa1ed3cb442819f8c46b371df433a,

title = "A Dependency Parser for Tweets",

abstract = "We describe a new dependency parser for English tweets, TWEEBOPARSER. The parser builds on several contributions: new syntactic annotations for a corpus of tweets (TWEEBANK), with conventions informed by the domain; adaptations to a statistical parsing algorithm; and a new approach to exploiting out-of-domain Penn Treebank data. Our experiments show that the parser achieves over 80% unlabeled attachment accuracy on our new, high-quality test set and measure the benefit of our contributions.Our dataset and parser can be found at http://www.ark.cs.cmu.edu/TweetNLP.",

author = "Lingpeng Kong and Nathan Schneider and Swabha Swayamdipta and Archna Bhatia and Chris Dyer and Smith, {Noah A.}",

year = "2014",

month = oct,

day = "1",

language = "English",

pages = "1001--1012",

booktitle = "Proceedings of the Conference on Empirical Methods in Natural Language Processing",

publisher = "Association for Computational Linguistics",

}

TY - GEN

T1 - A Dependency Parser for Tweets

AU - Kong, Lingpeng

AU - Schneider, Nathan

AU - Swayamdipta, Swabha

AU - Bhatia, Archna

AU - Dyer, Chris

AU - Smith, Noah A.

PY - 2014/10/1

Y1 - 2014/10/1

N2 - We describe a new dependency parser for English tweets, TWEEBOPARSER. The parser builds on several contributions: new syntactic annotations for a corpus of tweets (TWEEBANK), with conventions informed by the domain; adaptations to a statistical parsing algorithm; and a new approach to exploiting out-of-domain Penn Treebank data. Our experiments show that the parser achieves over 80% unlabeled attachment accuracy on our new, high-quality test set and measure the benefit of our contributions.Our dataset and parser can be found at http://www.ark.cs.cmu.edu/TweetNLP.

AB - We describe a new dependency parser for English tweets, TWEEBOPARSER. The parser builds on several contributions: new syntactic annotations for a corpus of tweets (TWEEBANK), with conventions informed by the domain; adaptations to a statistical parsing algorithm; and a new approach to exploiting out-of-domain Penn Treebank data. Our experiments show that the parser achieves over 80% unlabeled attachment accuracy on our new, high-quality test set and measure the benefit of our contributions.Our dataset and parser can be found at http://www.ark.cs.cmu.edu/TweetNLP.

M3 - Conference contribution

SP - 1001

EP - 1012

BT - Proceedings of the Conference on Empirical Methods in Natural Language Processing

PB - Association for Computational Linguistics

CY - Doha, Qatar

ER -

A Dependency Parser for Tweets

Abstract

Access to Document

Fingerprint

Cite this