A Dependency Parser for Tweets

@inproceedings{Kong2014ADP,
  title={A Dependency Parser for Tweets},
  author={Lingpeng Kong and Nathan Schneider and Swabha Swayamdipta and Archna Bhatia and Chris Dyer and Noah A. Smith},
  booktitle={EMNLP},
  year={2014}
}
  • Lingpeng Kong, Nathan Schneider, +3 authors Noah A. Smith
  • Published in EMNLP 2014
  • Computer Science
  • 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… CONTINUE READING
    195 Citations

    Figures, Tables, and Topics from this paper

    Parsing Tweets into Universal Dependencies
    • 31
    • PDF
    tweeDe – A Universal Dependencies treebank for German tweets
    • 3
    • Highly Influenced
    • PDF
    Dependency Parsing for Tweets
    • 2
    • Highly Influenced
    The Denoised Web Treebank: Evaluating Dependency Parsing under Noisy Input Conditions
    • 10
    • Highly Influenced
    • PDF
    Foreebank: Syntactic Analysis of Customer Support Forums
    • 23
    • Highly Influenced
    • PDF
    Parse Imputation for Dependency Annotations
    • 7
    • PDF
    An Evaluation of Parser Robustness for Ungrammatical Sentences
    • 9
    • Highly Influenced
    • PDF
    Arabic Tweets Treebanking and Parsing: A Bootstrapping Approach
    • 3
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 69 REFERENCES
    From News to Comment: Resources and Benchmarks for Parsing the Language of Web 2.0
    • 82
    • Highly Influential
    • PDF
    #hardtoparse: POS Tagging and Parsing the Twitterverse
    • 125
    • Highly Influential
    • PDF
    An Empirical Comparison of Parsing Methods for Stanford Dependencies
    • 26
    • PDF
    Simple Semi-supervised Dependency Parsing
    • 489
    • PDF
    Training Parsers on Incompatible Treebanks
    • 16
    • PDF
    Building a Treebank for French
    • 514
    • PDF
    Stacking Dependency Parsers
    • 100
    • PDF
    Three New Probabilistic Models for Dependency Parsing: An Exploration
    • 692
    • PDF
    Overview of the 2012 Shared Task on Parsing the Web
    • 175
    • PDF
    Experiments with a Higher-Order Projective Dependency Parser
    • 266
    • PDF