Survey on Text Transformation using Bi-LSTM in Natural Language Processing with Text Data
Main Article Content
Abstract
Communication using text can be understood by human beings as language plays a vital role in their life. Computers need to understand such human readable languages in order to explore documents in a wider manner. For such cases, machine learning algorithms as well as natural language processing algorithms can be used. Computers understand the human readable language and convert them as machine readable form. Replication of data stands as a most challenging problem in document exploration as the document may contain many repetitive words. The system makes use of classifier named LSTM to remove the words appearing frequently in the entire document. Firstly the text is transformed using NLP techniques followed by feature extraction and finally Bi-LSTM is used to classify the text data. LSTM mainly focus on reduction of repetitive words from the entire document and also maintains the integrity of the document. Bi-Lstm is an effective method to connect two different independent RNN together that helps to follow the sequence of statement front and back path every now and then.Multi directional ways of running the code will help in future prediction by saving the sentence for future purpose also.When the independent hidden states are joined it will be preserved for future and also past search. Although the word count is reduced, content of the word document is maintained in the LSTM method which stands as a major advantage. The experimental results showcase the efficacy of the system.
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.