Abstract:
Text classification is a construction problem of models which can classify new documents into predefined classes. It is important before text mining that we know what is the most important data that we require for our research. Text mining has become an essential tool for biomedical research. Our project aims to identify the gene-disease relationship using natural language processing techniques and word embeddings. Assignment of high-dimensional vectors (embeddings) to words in a text corpus in a way that preserves their syntactic and semantic relationships is one of the most fundamental techniques in natural language processing (NLP). We present a completely generic model based on statistical word embeddings, which shows the gene similarity and proves the gene-disease relationship using word analogies.
