CFGs-2-NLU: Sequence-to-Sequence Learning for Mapping Utterances to Semantics and Pragmatics

@article{Summerville2016CFGs2NLUSL,
  title={CFGs-2-NLU: Sequence-to-Sequence Learning for Mapping Utterances to Semantics and Pragmatics},
  author={Adam James Summerville and James Owen Ryan and Michael Mateas and Noah Wardrip-Fruin},
  journal={ArXiv},
  year={2016},
  volume={abs/1607.06852}
}
In this paper, we present a novel approach to natural language understanding that utilizes context-free grammars (CFGs) in conjunction with sequence-to-sequence (seq2seq) deep learning. Specifically, we take a CFG authored to generate dialogue for our target application for NLU, a videogame, and train a long short-term memory (LSTM) recurrent neural network (RNN) to map the surface utterances that it produces to traces of the grammatical expansions that yielded them. Critically, this CFG was… CONTINUE READING
4
Twitter Mentions

Similar Papers

References

Publications referenced by this paper.
SHOWING 1-10 OF 21 REFERENCES

Designing natural-language game conversations

J. Lessard
  • Proc. DiGRAFDG
  • 2016
VIEW 2 EXCERPTS

TensorFlow: Large-scale machine learning on heterogeneous systems (2015), http://tensorflow.org/, software available from tensorflow.org

M Abadi
  • 2015
VIEW 1 EXCERPT