Sentiment Classification of Documents in Serbian: The Effects of Morphological Normalization and Word Embeddings

An open issue in the sentiment classification of texts written in Serbian is the effect of different forms of morphological normalization and the usefulness of leveraging large amounts of unlabeled texts. In this paper, we assess the impact of lemmatizers and stemmers for Serbian on classifiers trai...

ver descrição completa

Detalhes bibliográficos

Principais autores:	V. Batanović, B. Nikolić
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Telecommunications Society, Academic Mind 2017-11-01
Colecção:	Telfor Journal
Assuntos:	comparative evaluation lemmatization morphology sentiment analysis stemming word embeddings
Acesso em linha:	http://journal.telfor.rs/Published/Vol9No2/Vol9No2_A6.pdf
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!