A Knowledge-Based Language Model: Deducing Grammatical Knowledge in a Multi-Agent Language Acquisition Simulation

TL;DR

This paper introduces MODOMA, a multi-agent system for unsupervised language acquisition that models grammatical learning through agent interactions, demonstrating successful acquisition of grammatical categories from machine-generated data.

Contribution

The paper presents a novel multi-agent framework that explicitly models grammatical knowledge acquisition in a computational setting, combining statistical and rule-based methods.

Findings

Functional and content categories can be acquired from varied data

Patterns similar to human language acquisition are observed in machine data

The system successfully models discrete grammatical categories

Abstract

This paper presents an initial study performed by the MODOMA system. The MODOMA is a computational multi-agent laboratory environment for unsupervised language acquisition experiments such that acquisition is based on the interaction between two language models, an adult and a child agent. Although this framework employs statistical as well as rule-based procedures, the result of language acquisition is a knowledge-based language model, which can be used to generate and parse new utterances of the target language. This system is fully parametrized and researchers can control all aspects of the experiments while the results of language acquisition, that is, the acquired grammatical knowledge, are explicitly represented and can be consulted. Thus, this system introduces novel possibilities for conducting computational language acquisition experiments. The experiments presented by this paper demonstrate that functional and content categories can be acquired and represented by the daughter agent based on training and test data containing different amounts of exemplars generated by the adult agent. Interestingly, similar patterns, which are well-established for human-generated data, are also found for these machine-generated data. As the procedures resulted in the successful acquisition of discrete grammatical categories by the child agent, these experiments substantiate the validity of the MODOMA approach to modelling language acquisition.