Jun Tani
2011
Emergence of hierarchical structure mirroring linguistic composition in a recurrent neural networkdoi.orgPDF
Neural Networks 24(4):311--320, 2011
We show that a Multiple Timescale Recurrent Neural Network (MTRNN) can acquire the capabilities to recognize, generate, and correct sentences by self-organizing in a way that mirrors the hierarchical structure of sentences: characters grouped into words, and words ...
2010
Autonomous Mental Development, IEEE Transactions on 2(3):167--195, 2010
Abstract This position paper proposes that the study of embodied cognitive agents, such as humanoid robots, can advance our understanding of the cognitive development of complex sensorimotor, linguistic, and social learning skills. This in turn will benefit the design of ...
2005
Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processesdoi.orgPDF
Adaptive Behavior 13(1):33--52, 2005
We present a novel connectionist model for acquiring the semantics of a simple language through the behavioral experiences of a real robot. We focus on the ``compositionality'' of semantics and examine how it can be generated through experiments. Our experimental results showed ...MORE ⇓
We present a novel connectionist model for acquiring the semantics of a simple language through the behavioral experiences of a real robot. We focus on the ``compositionality'' of semantics and examine how it can be generated through experiments. Our experimental results showed that the essential structures for situated semantics can self-organize themselves through dense interactions between linguistic and behavioral processes whereby a certain generalization in learning is achieved. Our analysis of the acquired dynamical structures indicates that an equivalence of compositionality appears in the combinatorial mechanics self-organized in the neuronal nonlinear dynamics. The manner in which this mechanism of compositionality, based on dynamical systems, differs from that considered in conventional linguistics and other synthetic computational models, is discussed in this paper.
2004
A Holistic Approach to Compositional Semantics: a connectionist model and robot experimentsPDF
Advances in Neural Information Processing Systems 16, 2004
We present a novel connectionist model for acquiring the semantics of language through the behavioral experiences of a real robot. We focus on the ``compositionality'' of semantics, which is a fundamental characteristic of human language, namely, the fact that we can understand ...MORE ⇓
We present a novel connectionist model for acquiring the semantics of language through the behavioral experiences of a real robot. We focus on the ``compositionality'' of semantics, which is a fundamental characteristic of human language, namely, the fact that we can understand the meaning of a sentence as a combination of the meanings of words. The essential claim is that a compositional semantic representation can be self-organized by generalizing correspondences between sentences and behavioral patterns. This claim is examined and confirmed through simple experiments in which a robot generates corresponding behaviors from unlearned sentences by analogy with the correspondences between learned sentences and behaviors.
A Connectionist Approach to Learn Association between Sentences and Behavioral Patterns of a RobotPDF
SAB04, pages 467-476, 2004
We focus on the ``compositionality'' of semantics, a fundamental characteristic of human language, which is the ability to understand the meaning of a sentence as a combination of the meanings of words. We also pay much attention to the ``embodiment'' of a robot, which means that ...MORE ⇓
We focus on the ``compositionality'' of semantics, a fundamental characteristic of human language, which is the ability to understand the meaning of a sentence as a combination of the meanings of words. We also pay much attention to the ``embodiment'' of a robot, which means that the robot should acquire semantics which matches its body, or sensory-motor system. The essential claim is that an embodied compositional semantic representation can be self-organized from generalized correspondences between sentences and behavioral patterns. This claim is examined and confirmed through simple experiments in which a robot generates corresponding behaviors from unlearned sentences by analogy with the correspondences between learned sentences and behaviors.