Repository logo
Communities & Collections
All of DSpace
  • English
  • العربية
  • বাংলা
  • Català
  • Čeština
  • Deutsch
  • Ελληνικά
  • Español
  • Suomi
  • Français
  • Gàidhlig
  • हिंदी
  • Magyar
  • Italiano
  • Қазақ
  • Latviešu
  • Nederlands
  • Polski
  • Português
  • Português do Brasil
  • Srpski (lat)
  • Српски
  • Svenska
  • Türkçe
  • Yкраї́нська
  • Tiếng Việt
Log In
Have you forgotten your password?
  1. Home
  2. Browse by Author

Browsing by Author "Verma, M."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Results Per Page
  • Sort Options
  • No Thumbnail Available
    Item
    Contextual Code-Mixed Translations with LLM-Based Data Augmentation
    (Institute of Electrical and Electronics Engineers Inc., 2025) Jinkathoti, M.; Verma, M.; Anand Kumar, M.; Adnan, M.
    Code-mixed conversational translation presents unique challenges for neural machine translation (NMT) systems due to its context-dependent nature and linguistic complexity. This paper investigates context-aware translation approaches for Hinglish-to-English code-mixed text, focusing on the comparative performance of the fine-tuned State-Of-The-Art (SOTA) language models, and proposes an approach that incorporates contextual information through a novel preprocessing technique and augmented prompt-based synthetically generated training data. With the help of comprehensive experimentation conducted across distinct configurations using two SOTA Mistral-7B-v0.3 and IndicTrans2 models, the findings demonstrate that Mistral-7Bv0.3 fine-tuned with context-enriched data and synthetic examples achieves state-of-the-art performance with 14.3% improvement over previous approaches. Furthermore, it is observed that in domain-specific patterns in optimal model configuration: conversational data benefits most from contextaware models with synthetic data augmentation, while nonconversational translation performs optimally with syntheticaugmented datasets without contextual enrichment. This research contributes valuable insights into the design of effective translation systems for code-mixed language and establishes new benchmarks for this increasingly important domain of multilingual NLP. © 2025 IEEE.
  • No Thumbnail Available
    Item
    Protease: Enzyme-aided value-addition in food processing industries
    (Nova Science Publishers, Inc., 2014) Raval, R.; Raval, K.; Brar, S.K.; Verma, M.
    Environmental and economic apprehensions behoove a reduction in food processing wastes and processing of food residuals to new value added products, enzyme being one of the means of obtaining the same. In this chapter we intend to exemplify the initiatives engendered by different groups to confront the issue of waste disposal and searching a more environment friendly method of handling the bio wastes. This has been elaborated by the panoramic view of the waste generated worldwide. In addition different enzymes produced using the industrial waste has been discussed. In the subsequent section, the trailing towards protease has been made. In continuation, an initiative made by different food based industries in the employment of protease in degradation of the industrial wastes has been touched on upon in the first section of the chapter. In the second section, the research on the use of various organic wastes generated by the food industries for the protease production by solid state fermentation has been discussed. This would in turn help in value addition of the organic waste generated. © 2014 by Nova Science Publishers, Inc. All rights reserved.

Maintained by Central Library NITK | DSpace software copyright © 2002-2026 LYRASIS

  • Privacy policy
  • End User Agreement
  • Send Feedback
Repository logo COAR Notify