Extracting word synonyms from text using neural approaches
Author
Source
The International Arab Journal of Information Technology
Issue
Vol. 17, Issue 1 (31 Jan. 2020), pp.45-51, 7 p.
Publisher
Zarqa University Deanship of Scientific Research
Publication Date
2020-01-31
Country of Publication
Jordan
No. of Pages
7
Main Subjects
Information Technology and Computer Science
Topics
Abstract EN
Extracting synonyms from textual corpora using computational techniques is an interesting research problem in the Natural Language Processing (NLP) domain.
Neural techniques (such as Word2Vec) have been recently utilized to produce distributional word representations (also known as word embeddings) that capture semantic similarity/relatedness between words based on linear context.
Nevertheless, using these techniques for synonyms extraction poses many challenges due to the fact that similarity between vector word representations does not indicate only synonymy between words, but also other sense relations as well as word association or relatedness.
In this paper, we tackle this problem using a novel 2-step approach.
We first build distributional word embeddings using Word2Vec then use the induced word embeddings as an input to train a feedforward neutral network using annotated dataset to distinguish between synonyms and other semantically related words.
American Psychological Association (APA)
Muhammad, Nurah. 2020. Extracting word synonyms from text using neural approaches. The International Arab Journal of Information Technology،Vol. 17, no. 1, pp.45-51.
https://search.emarefa.net/detail/BIM-955407
Modern Language Association (MLA)
Muhammad, Nurah. Extracting word synonyms from text using neural approaches. The International Arab Journal of Information Technology Vol. 17, no. 1 (Jan. 2020), pp.45-51.
https://search.emarefa.net/detail/BIM-955407
American Medical Association (AMA)
Muhammad, Nurah. Extracting word synonyms from text using neural approaches. The International Arab Journal of Information Technology. 2020. Vol. 17, no. 1, pp.45-51.
https://search.emarefa.net/detail/BIM-955407
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 50-51
Record ID
BIM-955407