WORD VECTOR USING R-ADAM OPTIMIZATION FUNCTION
DOI:
https://doi.org/10.61841/dq5z7f16Keywords:
Word2Vec, CBOW, skip-gram, word embeddings, machine translations, text summarization, Rectified Adam optimization functionAbstract
There has always been a strong interest in expressing notations to present vocabulary of a language in linguistics. This process is quite challenging because of high computational requirements, and the dimensionality curse. We use a word to vector approach to process text which can be best defined as a two-layered neural network. A text corpus will be provided as an input and a set of vectors representing features of words will be obtained as an output. It is not a deep neural network which allows it to be trained quickly compared to other neural network architectures. It embeds the words in numeric form which neural networks can consume. Continuous Bag of Words (CBOW) and Skip-gram models for word vector representation show immense success in capturing the semantic and syntactic relationships between words of a given language. These models show immense success in capturing the semantic and syntactic relationships between words of a given language. However, there is still scope of improvement in the domain of vector space representation. We propose to apply the recently introduced rectified Adam optimization function in place of the RMSprop optimization function. The function shows promising outcomes in terms of training times and accuracy for large datasets.
Downloads
References
[1] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient Estimation of Word Representations in Vector Space. In Proceedings of Workshop at ICLR, 2013
[2] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. Distributed Representations of Words and Phrases and their Compositionality. In Proceedings of NIPS, 2013.
[3] G. E. Hinton and R. R. Salakhutdinov, “Reducing the dimensionality of data with neural networks,” Science, vol. 313, no. 5786, pp. 504-507 2015.
[4] F. Sebastiani, “Machine learning in automated text categorization,” ACM Comput. Surv., vol. 34, pp. 1–47, 2002.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
