Interactive Language Learning by Robots: The Transition from Babbling to Word Forms

@article{Lyon2012InteractiveLL,
  title={Interactive Language Learning by Robots: The Transition from Babbling to Word Forms},
  author={Caroline Lyon and Chrystopher L. Nehaniv and Joe Saunders},
  journal={PLoS ONE},
  year={2012},
  volume={7}
}
The advent of humanoid robots has enabled a new approach to investigating the acquisition of language, and we report on the development of robots able to acquire rudimentary linguistic skills. Our work focuses on early stages analogous to some characteristics of a human child of about 6 to 14 months, the transition from babbling to first word forms. We investigate one mechanism among many that may contribute to this process, a key factor being the sensitivity of learners to the statistical… 

Figures and Tables from this paper

The ITALK Project: A Developmental Robotics Approach to the Study of Individual, Social, and Linguistic Learning
TLDR
Results are presented from a multidisciplinary research project on the integration and transfer of language knowledge into robots as an empirical paradigm for the study of language development in both humans and humanoid robots and show that the mutual scaffolding of social learning, individual learning, and linguistic capabilities creates the context, conditions, and requisites for learning in each domain.
Observing and Modeling Developing Knowledge and Uncertainty During Cross-Situational Word Learning
TLDR
Accuracy and uncertainty over time is examined in a version of the cross-situational learning task in which words are tested throughout training, as well as in a final test, to examine how well the online response trajectories match recent hypothesis- and association-based computational models of word learning.
Learning to interact and interacting to learn: Active statistical learning in human-robot interaction
TLDR
A real-time human-robot interaction paradigm was developed in which a robot learner acquired lexical knowledge from a human teacher through free-flowing interaction, which showed that more talking and looking acts from the robot, including those immature behaviors such as saying non-sense words or looking at random targets, motivated human teachers to be more engaged in the interaction.
An Alternative to Mapping a Word onto a Concept in Language Acquisition: Pragmatic Frames
TLDR
This theoretical paper proposes an alternative mechanism for word learning that involves a sequence of actions and verbal behaviors that are co-constructed with a partner to achieve a joint goal, and embeds it in current language learning approaches.
A Formal Approach to Social Learning: Exploring Language Acquisition Through Imitation
The topic of this thesis is learning through social interaction, consisting of experiments that focus on word acquisition through imitation, and a formalism aiming to provide stronger theoretical
Embodied Language Learning and Cognitive Bootstrapping: Methods and Design Principles
TLDR
The purpose of this article is to bring together diverse but complementary accounts of research methods that jointly contribute to the understanding of cognitive development and in particular, language acquisition in robots.
Dialogues as Procedural Skills
Early dialogues are learned as procedural skills, and have a special role in the evolution of language. Vocal turn-taking by marmoset monkeys, which resembles turn-taking by human infants, serves as
Interaction and experience in enactive intelligence and humanoid robotics
We overview how sensorimotor experience can be operationalized for interaction scenarios in which humanoid robots acquire skills and linguistic behaviours via enacting a “form-of-life” in interaction
Why Robots Should Be Social: Enhancing Machine Learning through Social Human-Robot Interaction
TLDR
This work shows how additional social cues in social machine learning can result in people offering better quality learning input to artificial systems, resulting in improved learning performance.
...
...

References

SHOWING 1-10 OF 82 REFERENCES
Preparing to Talk: Interaction between a Linguistically Enabled Agent and a Human Teacher
TLDR
A simulation of the transition from babbling to the recognition of first word forms in a simulated robot interacting with a human teacher precedes interactions with the real iCub robot.
From babbling towards first words: The emergence of speech in a robot in real-time interaction
TLDR
A system that simulates word form acquisition without meaning as a preliminary stage in language acquisition through interaction with a human teacher and a linguistically enabled synthetic agent, embodied in the iCub humanoid robot.
Building an adaptive spoken language interface for perceptually grounded human-robot interaction
TLDR
Because the robot community is international the robot should be able to speak multiple languages, it is demonstrated that the language model extends naturally to include both English and Japanese.
A dynamic systems approach to babbling and words
What is the developmental function of babbling in relation to language, if any? How is it related to the child’s first words, and can this relationship shed any light on the highly controversial
Mindful tutors: Linguistic choice and action demonstration in speech to infants and a simulated robot
It has been proposed that the design of robots might benefit from interactions that are similar to caregiver–child interactions, which is tailored to children’s respective capacities to a high
Language learning in infancy
Although immensely complex, speech is also a very efficient means of communication between humans. Understanding how we acquire the skills necessary for perceiving and producing speech remains an
Words in puddles of sound: modelling psycholinguistic effects in speech segmentation.
TLDR
A model ofspeech segmentation is presented that aims to reveal important sources of information for speech segmentation, and to capture psycholinguistic constraints on children's language perception, and constructs a lexicon based on information about utterance boundaries and deduces phonotactic constraints from the discovered lexicon.
What is Needed for a Robot to Acquire Grammar? Some Underlying Primitive Mechanisms for the Synthesis of Linguistic Ability
TLDR
The authors can deconstruct grammar to derive underlying primitive mechanisms, including serial processing, segmentation, categorization, compositionality, and forward planning that are necessary preparatory steps to reconstruct a working syntactic/semantic/pragmatic processor which can handle real language.
The ITALK project: Integration and Transfer of Action and Language Knowledge in Robots
The ITALK project intends to develop cognitive robotic agents, based on the iCub humanoid platform, that learn to handle and manipulate objects and tools autonomously, to cooperate and communicate
...
...