Word embedding and neural network on grammatical gender -- A case study of Swedish
This work bridges computational and general linguistics by applying standard methods to Swedish grammatical gender, but it is incremental as it uses existing techniques on a specific language case.
The study analyzed how word embeddings and neural networks capture grammatical gender information in Swedish, comparing computational results with existing linguistic hypotheses and analyzing model errors from a linguistic perspective.
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.