翻訳と辞書 |
Word2vec
Word2vec is a group of related models that are used to produce so-called word embeddings. These models are shallow, two-layer neural networks, that are trained to reconstruct linguistic contexts of words: the network is shown a word, and must guess at which words occurred in adjacent positions in an input text. The order of the remaining words is not important (bag-of-words assumption). After training, word2vec models can be used to map each word to a vector of typically several hundred elements, which represent that word's relation to other words. This vector is the neural network's hidden layer. Word2vec relies on either skip-grams or continuous bag of words (CBOW) to create neural word embeddings. It was created by a team of researchers led by Tomas Mikolov at Google. The algorithm has been subsequently analysed and explained by other researchers. ==Skip grams and CBOW==
Skip grams are word windows from which one word is excluded, an n-gram with gaps. With skip-grams, given a window size of words around a word , word2vec predicts contextual words ; i.e. in the notation of probability . Conversely, CBOW predicts the current word, given the context in the window, .
抄文引用元・出典: フリー百科事典『 ウィキペディア(Wikipedia)』 ■ウィキペディアで「Word2vec」の詳細全文を読む
スポンサード リンク
翻訳と辞書 : 翻訳のためのインターネットリソース |
Copyright(C) kotoba.ne.jp 1997-2016. All Rights Reserved.
|
|