Learning Language Games through Interaction

  title={Learning Language Games through Interaction},
  author={Sida I. Wang and Percy Liang and Christopher D. Manning},
  • Sida I. Wang, Percy Liang, Christopher D. Manning
  • Published 2016
  • Computer Science
  • ArXiv
  • We introduce a new language learning setting relevant to building adaptive natural language interfaces. [...] Key Method 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…Expand Abstract
    112 Citations

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Learning Adaptive Language Interfaces through Decomposition
    • 1
    • PDF
    Naturalizing a Programming Language via Interactive Learning
    • 39
    • PDF
    Coherence, Symbol Grounding and Interactive Task Learning
    • 2
    • PDF
    Teaching Machines to Classify from Natural Language Interactions
    • 1
    • PDF
    A Survey of Reinforcement Learning Informed by Natural Language
    • 40
    • PDF
    Improving Grounded Natural Language Understanding through Human-Robot Dialog
    • 21
    • PDF
    Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game
    • 3
    • PDF


    Learning and using language via recursive pragmatic reasoning about other agents
    • 44
    • Highly Influential
    • PDF
    Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation
    • 505
    • PDF
    Understanding Natural Language
    • 2,306
    • PDF
    Fast Online Lexicon Learning for Grounded Language Acquisition
    • 32
    • PDF
    Learning to interpret natural language navigation instructions from observations
    • 365
    Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions
    • 357
    • PDF
    Learning in the Rational Speech Acts Model
    • 32
    • PDF
    Grounding Verbs of Motion in Natural Language Commands to Robots
    • 62
    • PDF
    A Joint Model of Language and Perception for Grounded Attribute Learning
    • 269
    • PDF
    Learning Meanings of Words and Constructions, Grounded in a Virtual Game
    • 19
    • PDF