arXiv subjects

Maha Abu Rumman

Publications and source records attributed to Maha Abu Rumman.

2 recordsLinked to original sources

arXiv2024

Authenticity in Authorship: The Writer's Integrity Framework for Verifying Human-Generated Text

The "Writer's Integrity" framework introduces a paradigm shift in maintaining the sanctity of human-generated text in the realms of academia, research, and publishing. This innovative system circumvents the shortcomings of current AI detection tools by monitoring the writing process, rather than the product, capturing the distinct behavioral footprint of human authorship. Here, we offer a comprehensive examination of the framework, its development, and empirical results. We highlight its potential in revolutionizing the validation of human intellectual work, emphasizing its role in upholding academic integrity and intellectual property rights in the face of sophisticated AI models capable of emulating human-like text. This paper also discusses the implementation considerations, addressing potential user concerns regarding ease of use and privacy, and outlines a business model for tech companies to monetize the framework effectively. Through licensing, partnerships, and subscriptions, companies can cater to universities, publishers, and independent writers, ensuring the preservation of original thought and effort in written content. This framework is open source and available here, https://github.com/sanadv/Integrity.github.io

cs.CR↗

arXiv2023

An Ensemble Approach to Question Classification: Integrating Electra Transformer, GloVe, and LSTM

Natural Language Processing (NLP) has emerged as a crucial technology for understanding and generating human language, playing an essential role in tasks such as machine translation, sentiment analysis, and more pertinently, question classification. As a subfield within NLP, question classification focuses on determining the type of information being sought, a fundamental step for downstream applications like question answering systems. This study presents an innovative ensemble approach for question classification, combining the strengths of Electra, GloVe, and LSTM models. Rigorously tested on the well-regarded TREC dataset, the model demonstrates how the integration of these disparate technologies can lead to superior results. Electra brings in its transformer-based capabilities for complex language understanding, GloVe offers global vector representations for capturing word-level semantics, and LSTM contributes its sequence learning abilities to model long-term dependencies. By fusing these elements strategically, our ensemble model delivers a robust and efficient solution for the complex task of question classification. Through rigorous comparisons with well-known models like BERT, RoBERTa, and DistilBERT, the ensemble approach verifies its effectiveness by attaining an 80% accuracy score on the test dataset.

cs.CL↗