Review on Word2Vec Word Embedding Neural Net
Authors:
- 1 September 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 282-290
Abstract
The word2vec model consists of more useful applications in different NLP tasks. The semantic meaning given by word2vec for each word in vector representations has served useful task in machine learning text classification. They are employed in finding analogy, syntactic, and semantic analysis of words. Word2vec falls in two flavors CBOW and Skip-Gram. Given a context, they used to predict a word and vice versa are also true. In order to optimize the efficiency of word2vec, they have introduced two computational techniques namely hierarchical softmax and negative sampling. The proposed research work is more focused on introducing the models, computational technique, and various fields of word2vec applications. Word2vec is compared based on the metrics and their performance is evaluated by comparing with other existing models.Keywords
This publication has 18 references indexed in Scilit:
- Enhancing deep learning sentiment analysis with ensemble techniques in social applicationsExpert Systems with Applications, 2017
- A Targeted Retraining Scheme of Unsupervised Word Embeddings for Specific Supervised Tasks2017
- An approach to the use of word embeddings in an opinion classification taskExpert Systems with Applications, 2016
- Characterizing Diseases from Unstructured Text2016
- Sentiment Analysis on Chinese Health Forums: A Preliminary Study of Different Language Models2016
- A Comparison of Concept-base Model and Word Distributed Model as Word Association SystemProcedia Computer Science, 2016
- Learning Distributed Representations of Sentences from Unlabelled Data2016
- Matching User Accounts across Social Networks Based on Users MessageProcedia Computer Science, 2016
- Inferring Networks of Substitutable and Complementary Products2015
- Image-Based Recommendations on Styles and Substitutes2015