Semantic Parsing using Distributional Semantics and Probabilistic Logic

@inproceedings{Beltagy2014SemanticPU,
  title={Semantic Parsing using Distributional Semantics and Probabilistic Logic},
  author={Iz Beltagy and K. Erk and R. Mooney},
  booktitle={ACL 2014},
  year={2014}
}
  • Iz Beltagy, K. Erk, R. Mooney
  • Published in ACL 2014
  • Computer Science
  • We propose a new approach to semantic parsing that is not constrained by a fixed formal ontology and purely logical inference. Instead, we use distributional semantics to generate only the relevant part of an on-the-fly ontology. Sentences and the on-the-fly ontology are represented in probabilistic logic. For inference, we use probabilistic logic frameworks like Markov Logic Networks (MLN) and Probabilistic Soft Logic (PSL). This semantic parsing approach is evaluated on two tasks, Textual… CONTINUE READING
    22 Citations
    Natural Language Semantics using Probabilistic Logic
    • 4
    • PDF
    UTexas: Natural Language Semantics using Distributional Semantics and Probabilistic Logic
    • 20
    • PDF
    Learning to Make Inferences in a Semantic Parsing Task
    • 3
    • PDF
    New resources and ideas for semantic parser induction
    • PDF
    Tool comparison of semantic parsers
    • 1
    A Distributional Semantic Methodology for Enhanced Search in Historical Records: A Case Study on Smell
    • 2
    • PDF
    Explaining Natural Language query results
    • 2
    • PDF
    DBPal: A Fully Pluggable NL2SQL Training Pipeline
    • 6
    • PDF

    References

    SHOWING 1-10 OF 23 REFERENCES
    Probabilistic Soft Logic for Semantic Textual Similarity
    • 53
    • PDF
    Scaling Semantic Parsers with On-the-Fly Ontology Matching
    • 285
    • PDF
    Montague Meets Markov: Deep Semantics with Probabilistic Logical Form
    • 77
    • PDF
    Semantic Parsing on Freebase from Question-Answer Pairs
    • 1,017
    • PDF
    A short introduction to probabilistic soft logic
    • 179
    • Highly Influential
    • PDF
    Experimental Support for a Categorical Compositional Distributional Model of Meaning
    • 310
    • PDF
    Markov logic networks
    • 2,597
    • Highly Influential
    • PDF
    Wide-Coverage Semantic Analysis with Boxer
    • 298
    • Highly Influential
    • PDF
    Parsing the WSJ Using CCG and Log-Linear Models
    • 345
    • PDF
    Towards a Formal Distributional Semantics: Simulating Logical Calculi with Tensors
    • 85
    • PDF