![words that end with v e x words that end with v e x](https://i.pinimg.com/originals/e2/4f/93/e24f932baf6e52e305630d50c2cf8538.jpg)
The CBOW can be viewed as a ‘fill in the blank’ task, where the word embedding represents the way the word influences the relative probabilities of other words in the context window. In both architectures, word2vec considers both individual words and a sliding context window as it iterates over the corpus. Word2vec can utilize either of two model architectures to produce these distributed representations of words: Continuous Bag-Of-Words (CBOW) or continuously sliding skip-gram. Word2vec takes as its input a large corpus of text and produces a vector space, typically of several hundred dimensions, with each unique word in the corpus being assigned a corresponding vector in the space. These models are shallow, two-layer neural networks that are trained to reconstruct linguistic contexts of words. Word2vec is a group of related models that are used to produce word embeddings. This indicate the level of semantic similarity between the words, so for example the vectors for walk and ran are nearby, as are those for but and however and Berlin and Germany. In particular, words which appear in similar contexts are mapped to vectors which are nearby as measured by cosine similarity. Word2vec represents a word as a high-dimension vector of numbers which capture relationships between words. Word2vec was developed by Tomáš Mikolov and colleagues at Google and published in 2013. Once trained, such a model can detect synonymous words or suggest additional words for a partial sentence. The word2vec algorithm estimates these representations by modeling text in a large corpus. These vectors capture information about the meaning of the word and their usage in context.
![words that end with v e x words that end with v e x](https://2.bp.blogspot.com/-v77DHr9MOFE/TdhFWLercpI/AAAAAAAAAM8/UJKyckybB44/s1600/Final%2Bv%2BWords.jpg)
Word2vec is a technique in natural language processing (NLP) for obtaining vector representations of words.