Portal de Periódicos da CAPES

Semantic Author Name Disambiguation with Word Embeddings

2017; Springer Science+Business Media; Linguagem: Inglês

10.1007/978-3-319-67008-9_24

1611-3349

Mark-Christoph Müller,

Biomedical Text Mining and Ontologies

We present a supervised machine learning AND system which tackles semantic similarity between publication titles by means of word embeddings. Word embeddings are integrated as external components, which keeps the model small and efficient, while allowing for easy extensibility and domain adaptation. Initial experiments show that word embeddings can improve the Recall and F score of the binary classification sub-task of AND. Results for the clustering sub-task are less clear, but also promising and overall show the feasibility of the approach.