Browsing by Author "Shukla, S."

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    A Multilingual Multimedia Indian Sign Language Dictionary Tool
    (Asian Federation of Natural Language Processing, 2008) Dasgupta, T.; Shukla, S.; Kumar, S.; Diwakar, S.; Basu, A.
    This paper presents a cross platform multilingual multimedia Indian Sign Language (ISL) dictionary building tool. ISL is a linguistically under-investigated language with no source of well documented electronic data. Research on ISL linguistics also gets hindered due to a lack of ISL knowledge and the unavailability of any educational tools. Our system can be used to associate signs corresponding to a given text. The current system also facilitates the phonological annotation of Indian signs in the form of HamNoSys structure. The generated HamNoSys string can be given as input to an avatar module to produce an animated sign representation. © 2008 Asian Federation of Natural Language Processing. All rights reserved.
  • No Thumbnail Available
    Item
    Optimizing Solid Waste Management: A Holistic Approach by Informed Carbon Emission Reduction
    (Institute of Electrical and Electronics Engineers Inc., 2024) Hegde, S.; Sumith, N.; Pinto, T.; Shukla, S.; Patidar, V.
    Reducing carbon monoxide (CO) emissions is imperative for safeguarding human health and environment. CO adversely affects respiratory health, contributing to respiratory problems and, in severe cases, fatalities. Its reduction aligns with the broader efforts to combat climate change, as CO is often emitted alongside other greenhouse gases. Environmental consequences include air pollution and its detrimental impact on ecosystems. Compliance with emission standards is essential, and reducing Carbon emissions can lead to social and economic benefits, such as increased productivity and reduced healthcare costs. Moreover, the focus on emission reduction drives technological innovation, fostering the development of cleaner and sustainable technologies. In essence, addressing CO emissions is vital for creating a healthier, more sustainable future. However, in most of the cases, there has been no much importance given in scientific management of solid wastes. This has therefore resulted in large magnitude of carbon emission causing serious implications. This paper presents a novel approach to solid waste management, combining carbon emission assessment with advanced object detection technology. We develop an integrated waste management model that employs machine learning techniques for the identification and categorization of metals, non-metals, and plastics within the solid waste stream. To optimize waste sorting and recycling processes, we implement an efficient object detection system that leverages computer vision algorithms. This system enhances the precision of material identification within solid waste, thereby improving sorting accuracy. Additionally, we establish a database to quantify carbon emissions associated with distinct waste management methods, encompassing incineration, composting, recycling, bioremediation, and landfills is used for this work. The novelty of the work lies in the integration of CO2 emissions data and object detection resulting into a decision-making model, providing a holistic evaluation of the environmental impact of varied waste management scenarios. The formulation of recommendations for sustainable waste management practices based on the integrated assessment of carbon footprints and material identification is easy to implement in real world.The technical framework proposed here, aims to inform decision-makers on adopting environmentally conscious strategies for waste management. © 2024 The Authors. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.
  • No Thumbnail Available
    Item
    SELF-PERCEPT: Introspection Improves Large Language Models’ Detection of Multi-Person Mental Manipulation in Conversations
    (Association for Computational Linguistics (ACL), 2025) Khanna, D.; Seth, P.; Murali, S.; Guru, A.; Shukla, S.; Tyagi, T.; Chaurasia, S.; Ghosh, K.
    Mental manipulation is a subtle yet pervasive form of abuse in interpersonal communication, making its detection critical for safeguarding potential victims. However, due to manipulation’s nuanced and context-specific nature, identifying manipulative language in complex, multi-turn, and multi-person conversations remains a significant challenge for large language models (LLMs). To address this gap, we introduce the MultiManip dataset, comprising 220 multi-turn, multi-person dialogues balanced between manipulative and non-manipulative interactions, all drawn from reality shows that mimic real-world scenarios. For manipulative interactions, it includes 11 distinct manipulations depicting real-life scenarios. We conduct extensive evaluations of state-of-the-art LLMs, such as GPT-4o and Llama-3.1-8B, employing various prompting strategies. Despite their capabilities, these models often struggle to detect manipulation effectively. To overcome this limitation, we propose SELF-PERCEPT, a novel, two-stage prompting framework inspired by Self-Perception Theory, demonstrating strong performance in detecting multi-person, multi-turn mental manipulation. Our code and data are publicly available at https://github.com/danushkhanna/self-percept. ©2025 Association for Computational Linguistics.