University of North Texas
An Exploration of the Word2vec Algorithm: Creating a Vector Representation of a Language Vocabulary that Encodes Meaning and Usage Patterns in the Vector Space Structure
Abstract
dc:descriptionThis thesis is an exloration and exposition of a highly efficient shallow neural network algorithm called word2vec, which was developed by T. Mikolov et al. in order to create vector representations of a language vocabulary such that information about the meaning and usage of the vocabulary words is encoded in the vector space structure. Chapter 1 introduces natural language processing, vector representations of language vocabularies, and the word2vec algorithm. Chapter 2 reviews the basic mathematical theory of deterministic convex optimization. Chapter 3 provides background on some concepts from computer science that are used in the word2vec algorithm: Huffman trees, neural networks, and binary cross-entropy. Chapter 4 provides a detailed discussion of the word2vec algorithm itself and includes a discussion of continuous bag of words, skip-gram, hierarchical softmax, and negative sampling. Finally, Chapter 5 explores some applications of vector representations: word categorization, analogy completion, and language translation assistance.
Degree
thesis:*- Grantor dc:publisher
- University of North Texas
- Year dc:date
- 2016
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Le, Thu Anh
- Contributors dc:contributor
-
- Cherry, William, 1966-
- Ross, John Robert, 1938-
- Fishman, Lior, 1964-
Subjects
dc:subject × 15- Word2vec
- neural networks
- vector representation of language
- skip-gram
- bag of words
- hierarchical softmax
- negative sampling
- language translation
- Huffman trees
- binary cross-entropy
- optimization
- Mathematics
- Neural networks (Computer science)
- Natural language processing (Computer science)
- Computational linguistics.
Rights
dc:rights- Statement dc:rights
-
- Public
- Le, Thu Anh
- Copyright
- Copyright is held by the author, unless otherwise noted. All rights Reserved.
- Language dc:language
- English
Identifiers
dc:identifier.*- Identifier
-
local-cont-no: submission_234
https://digital.library.unt.edu/ark:/67531/metadc849728/
ark: ark:/67531/metadc849728