Learning Language Games through Interaction

@article{Wang2016LearningLG,
  title={Learning Language Games through Interaction},
  author={Sida I. Wang and Percy Liang and Christopher D. Manning},
  journal={ArXiv},
  year={2016},
  volume={abs/1606.02447}
}
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

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 75 CITATIONS

Do We Need Natural Language?: Exploring Restricted Language Interfaces for Complex Domains

VIEW 12 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following

VIEW 5 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

A Survey of Reinforcement Learning Informed by Natural Language

VIEW 1 EXCERPT
CITES BACKGROUND

FILTER CITATIONS BY YEAR

2016
2020

CITATION STATISTICS

  • 4 Highly Influenced Citations

  • Averaged 22 Citations per year from 2017 through 2019

  • 63% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 33 REFERENCES

Asking for Help Using Inverse Semantics

VIEW 1 EXCERPT

Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions

VIEW 1 EXCERPT