Abstract
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, a videogame, and train a long short-term memory (LSTM) recurrent neural network (RNN) to translate the surface utterances that it produces to traces of the grammatical expansions that yielded them. Critically, we already annotated the symbols in this grammar for the semantic and pragmatic considerations that our game’s dialogue manager operates over, allowing us to use the grammatical trace associated with any surface utterance to infer such information. From preliminary offline evaluation, we show that our RNN translates utterances to grammatical traces (and thereby meaning representations) with great accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). http://tensorflow.org/
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Lessard, J.: Designing natural-language game conversations. In: Proceedings DiGRA-FDG (2016)
Mateas, M., Stern, A.: Natural language understanding in Façade: surface-text processing. In: Proceedings TIDSE (2004)
Ryan, J., Mateas, M., Wardrip-Fruin, N.: Characters who speak their minds: dialogue generation in Talk of the Town. In: Proceedings AIIDE (2016)
Ryan, J., Mateas, M., Wardrip-Fruin, N.: A lightweight videogame dialogue manager. In: Proceedings DiGRA-FDG (2016)
Ryan, J., Seither, E., Mateas, M., Wardrip-Fruin, N.: Expressionist: an authoring tool for in-game text generation. In: Interactive Storytelling (2016)
Ryan, J.O., Summerville, A., Mateas, M., Wardrip-Fruin, N.: Toward characters who observe, tell, misremember, and lie. In: Proceedings Experimental AI in Games (2015)
Summerville, A.J., Ryan, J., Mateas, M., Wardrip-Fruin, N.: CFGs-2-NLU: sequence-to-sequence learning for mapping utterances to semantics and pragmatics. University of California, Santa Cruz, Technical report, UCSC-SOE-16-11 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Ryan, J., Summerville, A.J., Mateas, M., Wardrip-Fruin, N. (2016). Translating Player Dialogue into Meaning Representations Using LSTMs. In: Traum, D., Swartout, W., Khooshabeh, P., Kopp, S., Scherer, S., Leuski, A. (eds) Intelligent Virtual Agents. IVA 2016. Lecture Notes in Computer Science(), vol 10011. Springer, Cham. https://doi.org/10.1007/978-3-319-47665-0_38
Download citation
DOI: https://doi.org/10.1007/978-3-319-47665-0_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-47664-3
Online ISBN: 978-3-319-47665-0
eBook Packages: Computer ScienceComputer Science (R0)