ALGORITHMS FOR VECTOR REPRESENTATION OF TEXT
DOI:
https://doi.org/10.24867/06BE26StankovicKeywords:
encapsulation, word vectors, deeplearning, glove, word2vec, skipgram, cbowAbstract
Natural language processing (NLP) is an attractive area of computing intelligence. This paper will introduce several ways to convert text to vectors. There are two major categories, the first based on statistical methods and the second using neural networks. The advantage of vector representation is the ability to compare or further use such vectors in one of the machine learning methods. Vector representation maintains some semantics, so it is a convenient method for representing and comparing more complex text.
References
[1] Quoc Le, Tomas Mikolov, ``GloVe: Global Vectors for Word Representation'', Computer Science Department, Stanford University, Stanford, CA 94305, 2014.
[2] Quoc Le, Tomas Mikolov, ``Distributed Representations of Sentences and Documents'', Google Inc, 1600 Amphitheatre Parkway, Mountain View CA 94043, May 2014.
[3] Mikolov, Tomas & Chen, Kai & Corrado, G.s & Dean, Jeffrey. (2013). Efficient Estimation of Word Representations in Vector Space. Proceedings of Workshop at ICLR. 2013.
[2] Quoc Le, Tomas Mikolov, ``Distributed Representations of Sentences and Documents'', Google Inc, 1600 Amphitheatre Parkway, Mountain View CA 94043, May 2014.
[3] Mikolov, Tomas & Chen, Kai & Corrado, G.s & Dean, Jeffrey. (2013). Efficient Estimation of Word Representations in Vector Space. Proceedings of Workshop at ICLR. 2013.
Downloads
Published
2019-12-28
Issue
Section
Electrotechnical and Computer Engineering