Learning from Omission

Pragmatic reasoning allows humans to go beyond the literal meaning when interpret- ing language in context. Previous work has shown that such reasoning can improve the performance of already-trained language understanding systems. Here, we explore whether pragmatic reasoning during training can improve the quality of learned meanings. Our experiments on reference game data show that end-to-end pragmatic training produces more accurate utterance interpretation models, especially when data is sparse and language is complex.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[3]  Christopher Potts,et al.  Learning in the Rational Speech Acts Model , 2015, ArXiv.

[4]  Michael C. Frank,et al.  Predicting Pragmatic Reasoning in Language Games , 2012, Science.

[5]  Christopher Potts,et al.  Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding , 2017, TACL.

[6]  Siobhan Chapman.  Logic and Conversation , 2005 .

[7]  Guojun Lu,et al.  Shape-based image retrieval using generic Fourier descriptor , 2002, Signal Process. Image Commun..

[8]  T. Meo,et al.  Generating and Resolving Vague Color Reference , 2014 .

[9]  Samy Bengio,et al.  Context-Aware Captions from Context-Agnostic Supervision , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Michael C. Frank,et al.  Review Pragmatic Language Interpretation as Probabilistic Inference , 2022 .

[11]  Dan Klein,et al.  A Game-Theoretic Approach to Generating Spatial Descriptions , 2010, EMNLP.

[12]  Michael C. Frank,et al.  Inferring word meanings by assuming that speakers are informative , 2014, Cognitive Psychology.

[13]  Robert X D Hawkins,et al.  Conducting real-time multiplayer experiments on the web , 2014, Behavior Research Methods.

[14]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[15]  Christopher Potts,et al.  Learning to Generate Compositional Color Descriptions , 2016, EMNLP.

[16]  George Kingsley Zipf,et al.  Human behavior and the principle of least effort , 1949 .

[17]  Dan Klein,et al.  Reasoning about Pragmatics with Neural Listeners and Speakers , 2016, EMNLP.