On the Spontaneous Emergence of Discrete and Compositional Signals

We propose a general framework to study language emergence through signaling games with neural agents. Using a continuous latent space, we are able to (i) train using backpropagation, (ii) show that discrete messages nonetheless naturally emerge. We explore whether categorical perception effects follow and show that the messages are not compositional.

[1]  Tal Linzen,et al.  Issues in evaluating semantic spaces using word analogies , 2016, RepEval@ACL.

[2]  Eugene Kharitonov,et al.  EGG: a toolkit for research on Emergence of lanGuage in Games , 2019, EMNLP.

[3]  Thomas L. Griffiths,et al.  Evaluating vector-space models of analogy , 2017, CogSci.

[4]  Pieter Abbeel,et al.  Emergence of Grounded Compositional Language in Multi-Agent Populations , 2017, AAAI.

[5]  B. C. Griffith,et al.  The discrimination of speech sounds within and across phoneme boundaries. , 1957, Journal of experimental psychology.

[6]  Territoire Urbain,et al.  Convention , 1955, Hidden Nature.

[7]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[8]  Shane Steinert-Threlkeld,et al.  Toward the Emergence of Nontrivial Compositionality , 2020, Philosophy of Science.

[9]  Armin W. Schulz.  Signals: evolution, learning, and information , 2012 .

[10]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[11]  R. Paget.  The Origin of Speech , 1927, Nature.

[12]  Michael Franke,et al.  The Evolution of Compositionality in Signaling Games , 2015, Journal of Logic, Language and Information.

[13]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[14]  S. Kirby,et al.  Compression and communication in the cultural evolution of linguistic structure , 2015, Cognition.

[15]  Bart de Boer,et al.  Self-organization in vowel systems , 2000, J. Phonetics.

[16]  Alex Graves,et al.  Asynchronous Methods for Deep Reinforcement Learning , 2016, ICML.

[17]  Pieter Abbeel,et al.  Gradient Estimation Using Stochastic Computation Graphs , 2015, NIPS.

[18]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[19]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[20]  Yoshua Bengio,et al.  Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation , 2013, ArXiv.

[21]  Shane Steinert-Threlkeld,et al.  Compositional Signaling in a Complex World , 2016, Journal of Logic, Language and Information.

[22]  Eugene Kharitonov,et al.  Anti-efficient encoding in emergent communication , 2019, NeurIPS.

[23]  Ben Poole,et al.  Categorical Reparameterization with Gumbel-Softmax , 2016, ICLR.

[24]  Shane Steinert-Threlkeld,et al.  Paying Attention to Function Words , 2019, ArXiv.

[25]  Yee Whye Teh,et al.  The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables , 2016, ICLR.

[26]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[27]  Philippe Schlenker,et al.  Referential and general calls in primate semantics , 2021, Linguistics and Philosophy.

[28]  Nando de Freitas,et al.  Compositional Obverter Communication Learning From Raw Visual Input , 2018, ICLR.

[29]  M A Nowak,et al.  An error limit for the evolution of language , 1999, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[30]  Stephen Clark,et al.  Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input , 2018, ICLR.

[31]  Ivan Titov,et al.  Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols , 2017, NIPS.

[32]  S. Grossberg,et al.  Neural network models of categorical perception , 2000, Perception & psychophysics.

[33]  Alexander Peysakhovich,et al.  Multi-Agent Cooperation and the Emergence of (Natural) Language , 2016, ICLR.