Department of Computer Science

Machine Learning Research Group

University of Texas at Austin Artificial Intelligence Lab

Publications: Script Learning

An important part of understanding natural language is the incorporation of world knowledge. One possible way to encode world knowledge is in the form of scripts, which model stereotypical sequences of events. A script system learns scripts by generalizing such sequences of events from text. Recent work from our group in this area has explored new representations of events in scripts, and the use of recurrent neural networks to improve the learning of scripts.
  1. Advances in Statistical Script Learning
    [Details] [PDF] [Slides (PPT)]
    Karl Pichotta
    PhD Thesis, Department of Computer Science, The University of Texas at Austin, August 2017.
  2. Statistical Script Learning with Recurrent Neural Networks
    [Details] [PDF] [Poster]
    Karl Pichotta and Raymond J. Mooney
    In Proceedings of the Workshop on Uphill Battles in Language Processing (UBLP) at EMNLP 2016, Austin, TX, November 2016.
  3. Using Sentence-Level LSTM Language Models for Script Inference
    [Details] [PDF] [Slides (PPT)] [Slides (PDF)]
    Karl Pichotta and Raymond J. Mooney
    In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL-16), 279--289, Berlin, Germany, 2016.
  4. Learning Statistical Scripts with LSTM Recurrent Neural Networks
    [Details] [PDF] [Slides (PPT)] [Slides (PDF)]
    Karl Pichotta and Raymond J. Mooney
    In Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI-16), Phoenix, Arizona, February 2016.
  5. Statistical Script Learning with Recurrent Neural Nets
    [Details] [PDF] [Slides (PDF)]
    Karl Pichotta
    December 2015. PhD proposal, Department of Computer Science, The University of Texas at Austin.
  6. Statistical Script Learning with Multi-Argument Events
    [Details] [PDF] [Poster]
    Karl Pichotta and Raymond J. Mooney
    In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014), 220--229, Gothenburg, Sweden, April 2014.
  7. Schema acquisition from a single example
    [Details] [PDF]
    W. Ahn, W. F. Brewer and Raymond J. Mooney
    Journal of Experimental Psychology: Learning, Memory, and Cognition, 18:391-412, 1992.
  8. Learning Plan Schemata From Observation: Explanation-Based Learning for Plan Recognition
    [Details] [PDF]
    Raymond J. Mooney
    Cognitive Science, 14(4):483-509, 1990.
  9. Schema Acquisition from One Example: Psychological Evidence for Explanation-Based Learning
    [Details] [PDF]
    W. Ahn, Raymond J. Mooney, W.F. Brewer and G.F. DeJong
    In Proceedings of the Ninth Annual Conference of the Cognitive Science Society, 50-57, Seattle, WA, July 1987.
  10. Generalizing Explanations of Narratives into Schemata
    [Details] [PDF]
    Raymond J. Mooney
    In Proceedings of the Third International Machine Learning Workshop, 126--128, New Brunswick, New Jersey, 1985.
  11. Learning Schemata for Natural Language Processing
    [Details] [PDF]
    Raymond J. Mooney and Gerald F. DeJong
    In Proceedings of the Ninth International Joint Conference on Artificial Intelligence (IJCAI-85), 681-687, Los Angeles, CA, August 1985.
  12. Generalizing Explanations of Narratives into Schemata
    [Details] [PDF]
    Raymond J. Mooney
    Masters Thesis, Department of Computer Science, University of Illinois at Urbana-Champaign, 1985.