词向量开山之作2_Distributed Representations of Sentences and Documents.pdf
Manymachinelearningalgorithmsrequirethe
inputtoberepresentedasafixed-lengthfeature
vector.Whenitcomestotexts,oneofthemost
commonfixed-lengthfeaturesisbag-of-words.
Despitetheirpopularity,bag-of-wordsfeatures
havetwomajorweaknesses:theylosetheorderingofthewords
下载地址
用户评论