# Reinforcement Learning of Minimalist Numeral Grammars

## TL;DR

This paper presents a reinforcement learning approach for acquiring the syntactic and semantic features of English numerals using minimalist grammar, aiming to improve speech understanding in cognitive language technologies.

## Contribution

It introduces a novel reinforcement learning algorithm that integrates minimalist grammar with semantic parsing for numeral acquisition, bridging generative linguistics and machine learning.

## Key findings

- Successfully learned numeral syntax and semantics from utterance-meaning pairs
- Unified generative grammar with reinforcement learning for language acquisition
- Potential to enhance cognitive language technology systems

## Abstract

Speech-controlled user interfaces facilitate the operation of devices and household functions to laymen. State-of-the-art language technology scans the acoustically analyzed speech signal for relevant keywords that are subsequently inserted into semantic slots to interpret the user's intent. In order to develop proper cognitive information and communication technologies, simple slot-filling should be replaced by utterance meaning transducers (UMT) that are based on semantic parsers and a \emph{mental lexicon}, comprising syntactic, phonetic and semantic features of the language under consideration. This lexicon must be acquired by a cognitive agent during interaction with its users. We outline a reinforcement learning algorithm for the acquisition of the syntactic morphology and arithmetic semantics of English numerals, based on minimalist grammar (MG), a recent computational implementation of generative linguistics. Number words are presented to the agent by a teacher in form of utterance meaning pairs (UMP) where the meanings are encoded as arithmetic terms from a suitable term algebra. Since MG encodes universal linguistic competence through inference rules, thereby separating innate linguistic knowledge from the contingently acquired lexicon, our approach unifies generative grammar and reinforcement learning, hence potentially resolving the still pending Chomsky-Skinner controversy.