arXiv subjects

Vaibhav Khatavkar

Publications and source records attributed to Vaibhav Khatavkar.

5 recordsLinked to original sources

arXiv2025

CascadeNS: Confidence-Cascaded Neurosymbolic Model for Sarcasm Detection

Sarcasm detection in product reviews requires balancing domain-specific symbolic pattern recognition with deep semantic understanding. Symbolic representations capture explicit linguistic phenomena that are often decisive for sarcasm detection. Existing work either favors interpretable symbolic representation or semantic neural modeling, but rarely achieves both effectively. Prior hybrid methods typically combine these paradigms through feature fusion or ensembling, which can degrade performance. We propose CascadeNS, a confidence-calibrated neurosymbolic architecture that integrates symbolic and neural reasoning through selective activation rather than fusion. A symbolic semigraph handles pattern-rich instances with high confidence, while semantically ambiguous cases are delegated to a neural module based on pre-trained LLM embeddings. At the core of CascadeNS is a calibrated confidence measure derived from polarity-weighted semigraph scores. This measure reliably determines when symbolic reasoning is sufficient and when neural analysis is needed. Experiments on product reviews show that CascadeNS outperforms the strong baselines by 7.44%.

cs.CL↗

arXiv2024

Segmentation-free Connectionist Temporal Classification loss based OCR Model for Text Captcha Classification

Captcha are widely used to secure systems from automatic responses by distinguishing computer responses from human responses. Text, audio, video, picture picture-based Optical Character Recognition (OCR) are used for creating captcha. Text-based OCR captcha are the most often used captcha which faces issues namely, complex and distorted contents. There are attempts to build captcha detection and classification-based systems using machine learning and neural networks, which need to be tuned for accuracy. The existing systems face challenges in the recognition of distorted characters, handling variable-length captcha and finding sequential dependencies in captcha. In this work, we propose a segmentation-free OCR model for text captcha classification based on the connectionist temporal classification loss technique. The proposed model is trained and tested on a publicly available captcha dataset. The proposed model gives 99.80\% character level accuracy, while 95\% word level accuracy. The accuracy of the proposed model is compared with the state-of-the-art models and proves to be effective. The variable length complex captcha can be thus processed with the segmentation-free connectionist temporal classification loss technique with dependencies which will be massively used in securing the software systems.

cs.CV↗

arXiv2023

Researchers eye-view of sarcasm detection in social media textual content

The enormous use of sarcastic text in all forms of communication in social media will have a physiological effect on target users. Each user has a different approach to misusing and recognising sarcasm. Sarcasm detection is difficult even for users, and this will depend on many things such as perspective, context, special symbols. So, that will be a challenging task for machines to differentiate sarcastic sentences from non-sarcastic sentences. There are no exact rules based on which model will accurately detect sarcasm from many text corpus in the current situation. So, one needs to focus on optimistic and forthcoming approaches in the sarcasm detection domain. This paper discusses various sarcasm detection techniques and concludes with some approaches, related datasets with optimal features, and the researcher's challenges.

cs.CL↗

arXiv2023

Thematic context vector association based on event uncertainty for Twitter

Keyword extraction is a crucial process in text mining. The extraction of keywords with respective contextual events in Twitter data is a big challenge. The challenging issues are mainly because of the informality in the language used. The use of misspelled words, acronyms, and ambiguous terms causes informality. The extraction of keywords with informal language in current systems is pattern based or event based. In this paper, contextual keywords are extracted using thematic events with the help of data association. The thematic context for events is identified using the uncertainty principle in the proposed system. The thematic contexts are weighed with the help of vectors called thematic context vectors which signifies the event as certain or uncertain. The system is tested on the Twitter COVID-19 dataset and proves to be effective. The system extracts event-specific thematic context vectors from the test dataset and ranks them. The extracted thematic context vectors are used for the clustering of contextual thematic vectors which improves the silhouette coefficient by 0.5% than state of art methods namely TF and TF-IDF. The thematic context vector can be used in other applications like Cyberbullying, sarcasm detection, figurative language detection, etc.

cs.CL↗

arXiv2023

Effective Feature Extraction for Intrusion Detection System using Non-negative Matrix Factorization and Univariate analysis

An Intrusion detection system (IDS) is essential for avoiding malicious activity. Mostly, IDS will be improved by machine learning approaches, but the model efficiency is degrading because of more headers (or features) present in the packet (each record). The proposed model extracts practical features using Non-negative matrix factorization and chi-square analysis. The more number of features increases the exponential time and risk of overfitting the model. Using both techniques, the proposed model makes a hierarchical approach that will reduce the features quadratic error and noise. The proposed model is implemented on three publicly available datasets, which gives significant improvement. According to recent research, the proposed model has improved performance by 4.66% and 0.39% with respective NSL-KDD and CICD 2017.

cs.CR↗