A Distributional Semantics Approach to Implicit Language Learning

TL;DR

This paper demonstrates that distributional semantics significantly influences implicit language learning, showing that semantic regularities reflected in language use affect learnability, with models mirroring human learning patterns across different languages.

Contribution

It introduces a novel approach combining distributional semantics with neural networks to simulate and analyze implicit language learning behaviors.

Findings

Distributional information impacts concept availability in implicit learning.

Models trained on English and Chinese corpora replicate human learning patterns.

Semantic regularities reflected in language use influence learnability.

Abstract

In the present paper we show that distributional information is particularly important when considering concept availability under implicit language learning conditions. Based on results from different behavioural experiments we argue that the implicit learnability of semantic regularities depends on the degree to which the relevant concept is reflected in language use. In our simulations, we train a Vector-Space model on either an English or a Chinese corpus and then feed the resulting representations to a feed-forward neural network. The task of the neural network was to find a mapping between the word representations and the novel words. Using datasets from four behavioural experiments, which used different semantic manipulations, we were able to obtain learning patterns very similar to those obtained by humans.