Neural text embeddings provide dense vector representations of words and documents that encode various notions of semantic relatedness. Word2vec models typical similarity by representing words based on neighboring context words, while models like latent semantic analysis encode topical similarity through co-occurrence in documents. Dual embedding spaces can separately model both typical and topica
![Neural Text Embeddings for Information Retrieval (WSDM 2017)](https://cdn-ak-scissors.b.st-hatena.com/image/square/5d1ce60ceb7b5a1d3c9d8404506906d3dca96c10/height=288;version=1;width=512/https%3A%2F%2Fcdn.slidesharecdn.com%2Fss_thumbnails%2Fneuirtutorial-wsdm2017-170206010405-thumbnail.jpg%3Fwidth%3D640%26height%3D640%26fit%3Dbounds)