BITS Faculty Publications

Permanent URI for this communityhttp://localhost:4000/handle/123456789/1867

Browse

Filters

2024 - 20252

Settings

Author: search.filters.author.Chamola, VinaySubject: search.filters.subject.Deep learning

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    A detailed comparative analysis of automatic neural metrics for machine translation: bleurt & bertscore
    (IEEE, 2025-04) Chamola, Vinay; Gupta, Karunesh Kumar
    Bleurt a recently introduced metric that employs Bert, a potent pre-trained language model to assess how well candidate translations compare to a reference translation in the context of machine translation outputs. While traditional metrics like Bleu rely on lexical similarities, Bleurt leverages Bert's semantic and syntactic capabilities to provide more robust evaluation through complex text representations. However, studies have shown that Bert, despite its impressive performance in natural language processing tasks can sometimes deviate from human judgment, particularly in specific syntactic and semantic scenarios. Through systematic experimental analysis at the word level, including categorization of errors such as lexical mismatches, untranslated terms, and structural inconsistencies, we investigate how Bleurt handles various translation challenges. Our study addresses three central questions: What are the strengths and weaknesses of Bleurt, how do they align with Bert's known limitations, and how does it compare with the similar automatic neural metric for machine translation, BERTScore? Using manually annotated datasets that emphasize different error types and linguistic phenomena, we find that Bleurt excels at identifying nuanced differences between sentences with high overlap, an area where BERTScore shows limitations. Our systematic experiments, provide insights for their effective application in machine translation evaluation.
  • No Thumbnail Available
    Item
    QuARCS: Quantum Anomaly Recognition and Caption Scoring Framework for Surveillance Videos
    (IEEE, 2024-08) Chamola, Vinay
    Traditional surveillance video stream monitoring demands manual analysis, often leading to inaccuracies. While recent advancements have enabled automated analysis in surveillance video stream monitoring, challenges persist in achieving high accuracy and efficiency. Thus, an automated system is needed to monitor and report on video streams in real-time or retrospectively within surveillance networks, alleviating human error and inefficiency. Our paper, presents a comprehensive framework that integrates a hybrid quantum-classical anomaly detection system, a caption-generating model, and a novel Text-Driven Urgency Rating Model (T-DURM) trained using a newly created labelled dataset called UCFC-CUR which prioritises crimes based on their urgency. The hybrid classifier outperforms its direct classical counterpart by 7.7%. The aforementioned pipeline possesses the capability to identify anomalous occurrences from surveillance videos, generate a textual representation of the event, and assign a numerical value indicating the level of urgency associated with the specific anomaly. The hybrid anomaly detection model achieved an AUC of 82.80 surpassing the classical model’s AUC of 75.14. While the newly proposed T-DRUM achieves a R2 score of 0.982.