Department of Computer Science

Machine Learning Research Group

University of Texas at Austin Artificial Intelligence Lab

Publications: Combining Logical and Distributional Semantics

The Field of Distributional Semantics provides techniques for reasoning about the meanings of words and phrases based on usage statistics in large text corpora; however, these techniques typically fail to capture much of the logical structure of natural language. Purely logic-based approaches to natural language semantics, on the other hand, fail to capture many graded notions of word meaning. We are investigating methods to combine these two approaches to natural language semantics.
  1. Natural Language Semantics Using Probabilistic Logic
    [Details] [PDF] [Slides (PPT)] [Slides (PDF)]
    I. Beltagy
    PhD Thesis, Department of Computer Science, The University of Texas at Austin, December 2016.
  2. Representing Meaning with a Combination of Logical and Distributional Models
    [Details] [PDF]
    I. Beltagy and Stephen Roller and Pengxiang Cheng and Katrin Erk and Raymond J. Mooney
    The special issue of Computational Linguistics on Formal Distributional Semantics, 42(4), 2016.
  3. On the Proper Treatment of Quantifiers in Probabilistic Logic Semantics
    [Details] [PDF] [Slides (PPT)]
    I. Beltagy and Katrin Erk
    In Proceedings of the 11th International Conference on Computational Semantics (IWCS-2015), London, UK, April 2015.
  4. Natural Language Semantics using Probabilistic Logic
    [Details] [PDF] [Slides (PPT)]
    I. Beltagy
    October 2014. PhD proposal, Department of Computer Science, The University of Texas at Austin.
  5. UTexas: Natural Language Semantics using Distributional Semantics and Probabilistic Logic
    [Details] [PDF]
    I. Beltagy and Stephen Roller and Gemma Boleda and and Katrin Erk and Raymond J. Mooney
    In The 8th Workshop on Semantic Evaluation (SemEval-2014), 796--801, Dublin, Ireland, August 2014.
  6. Efficient Markov Logic Inference for Natural Language Semantics
    [Details] [PDF] [Poster]
    I. Beltagy and Raymond J. Mooney
    In Proceedings of the Fourth International Workshop on Statistical Relational AI at AAAI (StarAI-2014), 9--14, Quebec City, Canada, July 2014.
  7. Semantic Parsing using Distributional Semantics and Probabilistic Logic
    [Details] [PDF] [Poster]
    I. Beltagy and Katrin Erk and Raymond Mooney
    In Proceedings of ACL 2014 Workshop on Semantic Parsing (SP-2014), 7--11, Baltimore, MD, June 2014.
  8. Probabilistic Soft Logic for Semantic Textual Similarity
    [Details] [PDF] [Poster]
    I. Beltagy and Katrin Erk and Raymond J. Mooney
    In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL-14), 1210--1219, Baltimore, MD, 2014.
  9. Montague Meets Markov: Deep Semantics with Probabilistic Logical Form
    [Details] [PDF] [Slides (PPT)]
    I. Beltagy, Cuong Chau, Gemma Boleda, Dan Garrette, Katrin Erk, Raymond Mooney
    In Proceedings of the Second Joint Conference on Lexical and Computational Semantics (*Sem-2013), 11--21, Atlanta, GA, June 2013.
  10. Integrating Logical Representations with Probabilistic Information using Markov Logic
    [Details] [PDF] [Slides (PDF)]
    Dan Garrette, Katrin Erk, Raymond Mooney
    In Proceedings of the International Conference on Computational Semantics, 105--114, Oxford, England, January 2011.