Corpus ID: 5678214

Identifying Functional Relations in Web Text

@inproceedings{Lin2010IdentifyingFR,
  title={Identifying Functional Relations in Web Text},
  author={Thomas Lin and Mausam and Oren Etzioni},
  booktitle={EMNLP},
  year={2010}
}
  • Thomas Lin, Mausam, Oren Etzioni
  • Published in EMNLP 2010
  • Computer Science
  • Determining whether a textual phrase denotes a functional relation (i.e., a relation that maps each domain element to a unique range element) is useful for numerous NLP tasks such as synonym resolution and contradiction detection. Previous work on this problem has relied on either counting methods or lexico-syntactic patterns. However, determining whether a relation is functional, by analyzing mentions of the relation in a corpus, is challenging due to ambiguity, synonymy, anaphora, and other… CONTINUE READING
    40 Citations
    Semantic Relations Between Nominals
    • 46
    Interactive learning of relation extractors with weak supervision
    • 2
    Identifying Relations for Open Information Extraction
    • 1,112
    • PDF
    Open Information Extraction for Spanish Language based on Syntactic Constraints
    • 11
    • PDF
    Dependency-Based Open Information Extraction
    • 91
    • PDF
    Open Information Extraction from Dialogue Transcriptions
    Inference over the web
    • 1
    • PDF
    Commonsense from the Web: Relation Properties
    • 4
    • PDF

    References

    SHOWING 1-10 OF 32 REFERENCES
    Unsupervised Methods for Determining Object and Relation Synonyms on the Web
    • 110
    • PDF
    Scaling Textual Inference to the Web
    • 63
    • PDF
    The Tradeoffs Between Open and Traditional Relation Extraction
    • 396
    • PDF
    It's a Contradiction - no, it's not: A Case Study using Functional Relations
    • 75
    • PDF
    Open Information Extraction from the Web
    • 2,081
    • PDF
    Learning Arguments and Supertypes of Semantic Relations Using Recursive Patterns
    • 60
    • PDF
    Verbnet: a broad-coverage, comprehensive verb lexicon
    • 885
    WordNet : an electronic lexical database
    • 12,768
    • PDF