Knowledge-Guided Linguistic Rewrites for Inference Rule Verification

@inproceedings{Jain2016KnowledgeGuidedLR,
  title={Knowledge-Guided Linguistic Rewrites for Inference Rule Verification},
  author={Prachi Jain and Mausam},
  booktitle={HLT-NAACL},
  year={2016}
}
  • Prachi Jain, Mausam
  • Published in HLT-NAACL 2016
  • Computer Science
  • A corpus of inference rules between a pair of relation phrases is typically generated using the statistical overlap of argument-pairs associated with the relations (e.g., PATTY, CLEAN). We investigate knowledge-guided linguistic rewrites as a secondary source of evidence and find that they can vastly improve the quality of inference rule corpora, obtaining 27 to 33 point precision improvement while retaining substantial recall. The facts inferred using cleaned inference rules are 29-32 points… CONTINUE READING
    8 Citations

    Figures and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Open Information Extraction from Conjunctive Sentences
    • 25
    Extraction from Conjunctive Sentences
    Open Information Extraction Systems and Downstream Applications
    • Mausam
    • Computer Science
    • IJCAI
    • 2016
    • 87
    • PDF
    Extraction Systems and Downstream Applications
    • Mausam
    • 2016
    Type-Sensitive Knowledge Base Inference Without Explicit Type Supervision
    • 16
    • PDF

    References

    SHOWING 1-10 OF 31 REFERENCES
    Learning Verb Inference Rules from Linguistically-Motivated Evidence
    • 30
    • Highly Influential
    • PDF
    Adding Semantics to Data-Driven Paraphrasing
    • 50
    • PDF
    Natural Logic for Textual Inference
    • 157
    • PDF
    DIRT @SBT@discovery of inference rules from text
    • 551
    • PDF
    Learning First-Order Horn Clauses from Web Text
    • 174
    • Highly Influential
    • PDF
    Learning to "Read Between the Lines" using Bayesian Logic Programs
    • 23
    • Highly Influential
    • PDF
    Scaling Textual Inference to the Web
    • 63
    • Highly Influential
    • PDF
    RELLY: Inferring Hypernym Relationships Between Relational Phrases
    • 16
    • PDF
    Can we derive general world knowledge from texts
    • 123
    • PDF