Word embedding and neural network on grammatical gender -- A case study of Swedish

TL;DR

This paper investigates how word embeddings and neural networks capture Swedish grammatical gender, bridging computational and general linguistics by analyzing model performance and linguistic hypotheses.

Contribution

It demonstrates the capacity of word embeddings and neural networks to encode grammatical gender information in Swedish and compares computational results with linguistic theories.

Findings

Word embeddings encode grammatical gender information.

Neural networks can predict gender with reasonable accuracy.

Analysis of errors reveals linguistic insights.

Abstract

We analyze the information provided by the word embeddings about the grammatical gender in Swedish. We wish that this paper may serve as one of the bridges to connect the methods of computational linguistics and general linguistics. Taking nominal classification in Swedish as a case study, we first show how the information about grammatical gender in language can be captured by word embedding models and artificial neural networks. Then, we match our results with previous linguistic hypotheses on assignment and usage of grammatical gender in Swedish and analyze the errors made by the computational model from a linguistic perspective.