Learning Language Games through Interaction

We introduce a new language learning setting relevant to building adaptive natural language interfaces. It is inspired by Wittgenstein's language games: a human wishes to accomplish some task (e.g., achieving a certain configuration of blocks), but can only communicate with a computer, who performs the actual actions (e.g., removing all red blocks). The computer initially knows nothing about language and therefore must learn it from scratch through interaction, while the human adapts to the computer's capabilities. We created a game in a blocks world and collected interactions from 100 people playing it. First, we analyze the humans' strategies, showing that using compositionality and avoiding synonyms correlates positively with task performance. Second, we compare computer strategies, showing how to quickly learn a semantic parsing model from scratch, and that modeling pragmatics further accelerates learning for successful players.

[1]  Luke S. Zettlemoyer,et al.  Online Learning of Relaxed CCG Grammars for Parsing to Logical Form , 2007, EMNLP.

[2]  Raymond J. Mooney,et al.  Learning Synchronous Grammars for Semantic Parsing with Lambda Calculus , 2007, ACL.

[3]  Mark Steedman,et al.  Inducing Probabilistic CCG Grammars from Logical Form with Higher-Order Unification , 2010, EMNLP.

[4]  Gerhard Jäger,et al.  Game theory in semantics and pragmatics , 2012 .

[5]  Daniel Jurafsky,et al.  Learning to Follow Navigational Directions , 2010, ACL.

[6]  Percy Liang,et al.  Compositional Semantic Parsing on Semi-Structured Tables , 2015, ACL.

[7]  David L. Chen.  Fast Online Lexicon Learning for Grounded Language Acquisition , 2012, ACL.

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

[9]  Dan Klein,et al.  Learning Dependency-Based Compositional Semantics , 2011, CL.

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

[11]  Luke S. Zettlemoyer,et al.  Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions , 2013, TACL.

[12]  Ross A. Knepper,et al.  Asking for Help Using Inverse Semantics , 2014, Robotics: Science and Systems.

[13]  Peter Stone,et al.  Reinforcement learning , 2019, Scholarpedia.

[14]  Luke S. Zettlemoyer,et al.  Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars , 2005, UAI.

[15]  Andrew G. Barto,et al.  Reinforcement learning , 1998 .

[16]  Luke S. Zettlemoyer,et al.  A Joint Model of Language and Perception for Grounded Attribute Learning , 2012, ICML.

[17]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

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

[19]  Terry Winograd,et al.  Understanding natural language , 1974 .

[20]  Michael C. Frank,et al.  Learning and using language via recursive pragmatic reasoning about other agents , 2013, NIPS.

[21]  Stefanie Tellex,et al.  Grounding Verbs of Motion in Natural Language Commands to Robots , 2010, ISER.

[22]  E. Markman,et al.  Children's use of mutual exclusivity to constrain the meanings of words , 1988, Cognitive Psychology.

[23]  Christopher Potts,et al.  Emergence of Gricean Maxims from Multi-Agent Decision Theory , 2013, NAACL.

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

[25]  Luke S. Zettlemoyer,et al.  Reading between the Lines: Learning to Map High-Level Instructions to Commands , 2010, ACL.

[26]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[27]  Marko Dragojevic,et al.  Communication Accommodation Theory , 2015 .

[28]  Noah D. Goodman,et al.  Probabilistic Semantics and Pragmatics: Uncertainty in Language and Thought , 2015 .

[29]  Luke S. Zettlemoyer,et al.  Reinforcement Learning for Mapping Instructions to Actions , 2009, ACL.

[30]  Matthew R. Walter,et al.  Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation , 2011, AAAI.

[31]  Andrew Chou,et al.  Semantic Parsing on Freebase from Question-Answer Pairs , 2013, EMNLP.

[32]  Lauren E. Scissors,et al.  Language Style Matching Predicts Relationship Initiation and Stability , 2011, Psychological science.

[33]  Raymond J. Mooney,et al.  Learning to Interpret Natural Language Navigation Instructions from Observations , 2011, Proceedings of the AAAI Conference on Artificial Intelligence.

[34]  Jeff Orkin,et al.  Learning Meanings of Words and Constructions, Grounded in a Virtual Game , 2010, KONVENS.

[35]  L. Wittgenstein.  Philosophical investigations = Philosophische Untersuchungen , 1958 .