Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Distributed Representations, Simple Recurrent Networks, And Grammatical Structure
Machine Learning - Connectionist approaches to language learning
The Induction of Dynamical Recognizers
Machine Learning - Connectionist approaches to language learning
Language as a dynamical system
Mind as motion
Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Finite state automata and simple recurrent networks
Neural Computation
Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
| Hi-index | 0.00 |
We show that a Multiple Timescale Recurrent Neural Network (MTRNN) can acquire the capabilities of recognizing and generating sentences by self-organizing a hierarchical linguistic structure. There have been many studies aimed at finding whether a neural system such as the brain can acquire languages without innate linguistic faculties. These studies have found that some kinds of recurrent neural networks could learn grammar. However, these models could not acquire the capability of deterministically generating various sentences, which is an essential part of language functions. In addition, the existing models require a word set in advance to learn the grammar. Learning languages without previous knowledge about words requires the capability of hierarchical composition such as characters to words and words to sentences, which is the essence of the rich expressiveness of languages. In our experiment, we trained our model to learn language using only a sentence set without any previous knowledge about words or grammar. Our experimental results demonstrated that the model could acquire the capabilities of recognizing and deterministically generating grammatical sentences even if they were not learned. The analysis of neural activations in our model revealed that the MTRNN had self-organized the linguistic structure hierarchically by taking advantage of differences in the time scale among its neurons, more concretely, neurons that change the fastest represented "characters," those that change more slowly represented "words," and those that change the slowest represented "sentences."