Indian Journal of Computer Science

Open Access Open Access  Restricted Access Subscription Access

Product Copy Generation for Fashion Footwear Data


Affiliations
1 Data Scientist, Retail Strategic Initiatives, Retail Cluster, Tata Consultancy Services Pvt. Ltd., SIPCOT IT Park, Siruseri, Chennai - 603 103, Tamil Nadu, India
2 Principal Scientist, Retail Strategic Initiatives, Retail Cluster, Tata Consultancy Services Pvt. Ltd., Magnum SEZ IT Park, Pallikaranai Marshland, Kotivakkam, Chennai - 600 096, Tamil Nadu, India

   Subscribe/Renew Journal


Natural Language Generation is a specialized field of Artificial Intelligence (AI) that deals with generation of text, given a set of inputs, like text, image or both. It is also deals with training of a given algorithm or machine to learn about a particular information and build relevant set of information about it in the form of natural language or text, given an input, while validating the same. This technology has stirred up a storm in the field of AI and has a great impact on automation science.

Keywords

Bi-Directional and Autoregressive Transformer (BART), Convolutional Neural Network (CNN), Generative Pre-Trained (GPT), Long Short Term Memory (LSTM), Natural Language Generation (NLG), Product Copy Generation (PCG), Recurrent Neural Network (RNN).
User
Subscription Login to verify subscription
Notifications
Font Size

  • S. Dathathri, A. Madotto, J. Lan, J. Hung, E. Frank, P. Molino, J. Yosinski, and R. Liu, “Plug and play language models: A simple approach to controlled text generation,” 2019. [Online]. Available: https://arxiv.org/abs/1912.02164

  • P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W. Yih, T. Rocktäschel, S.Riedel, and D. Kiela, “Retrieval-augmented generation for knowledge-intensive NLP tasks,” 2020. [Online]. Available: https://arxiv.org/abs/2005.11401

  • T. Wolf, L. Debut, V. Sanh, J. Chaumond, C. Delangue, A. Moi, and P. Cistac et al., “HuggingFace's Transformers : State-of-the-art Natural Language Processing,” 2019. [Online]. Available: https://arxiv.org/abs/1910.03771

  • M. Lewis, Y. Liu, N. Goyal, M. Ghazvininejad, A. Mohamed, O.Levy, V. Stoyanov, and L. Zettlemoyer, “BART: Denoising sequence-to-sequence pre-training for Natural Language Generation, translation, and comprehension,” in Proc. of the 58th Annual Meeting of the Assoc. for Computational Linguistics, July 5-10, 2020, pp. 7871-7880. [Online]. Available: https://aclanthology.org/2020.acl-main.703.pdf

  • P. Gujjar J. and N. Kumar V., “Google Colaboratory: Tool for Deep Learning and Machine Learning Applications,” 2021. [Online]. Available: http://www.indianjournalofcomputerscience.com/index.php/tcsj/article/view/165408


Abstract Views: 114

PDF Views: 0




  • Product Copy Generation for Fashion Footwear Data

Abstract Views: 114  |  PDF Views: 0

Authors

Sudesna Baruah
Data Scientist, Retail Strategic Initiatives, Retail Cluster, Tata Consultancy Services Pvt. Ltd., SIPCOT IT Park, Siruseri, Chennai - 603 103, Tamil Nadu, India
Bagya Lakshmi V.
Principal Scientist, Retail Strategic Initiatives, Retail Cluster, Tata Consultancy Services Pvt. Ltd., Magnum SEZ IT Park, Pallikaranai Marshland, Kotivakkam, Chennai - 600 096, Tamil Nadu, India

Abstract


Natural Language Generation is a specialized field of Artificial Intelligence (AI) that deals with generation of text, given a set of inputs, like text, image or both. It is also deals with training of a given algorithm or machine to learn about a particular information and build relevant set of information about it in the form of natural language or text, given an input, while validating the same. This technology has stirred up a storm in the field of AI and has a great impact on automation science.

Keywords


Bi-Directional and Autoregressive Transformer (BART), Convolutional Neural Network (CNN), Generative Pre-Trained (GPT), Long Short Term Memory (LSTM), Natural Language Generation (NLG), Product Copy Generation (PCG), Recurrent Neural Network (RNN).

References





DOI: https://doi.org/10.17010/ijcs%2F2021%2Fv6%2Fi5%2F166513