Quora Question Pairs Identification and Insincere Questions Classification

Gontumukkala, Sai Surya Teja; Godavarthi, Yogeshwara Sai Varun; Gonugunta, Bhanu Rama Ravi Teja; Gupta, Deepa; Palaniswamy, Suja

doi:10.1109/icccnt54827.2022.9984492

Cited by 5 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The log loss for the XGBoost model was 0.35, while the log loss for the Siamese LSTM model was 0.21. Furthermore, Gontumukkala et al [19] proposed a method to overcome two drawbacks of Quora as the occurrence of duplicate questions that cause ambiguity and insincere questions that lessen the value of the site by suggesting a strategy to address these two issues using Deep Learning (DL) and Natural Language Processing (NLP) approaches. Bidirectional Long Short-Term Memory (BiLSTM) and Bi-Gated Recurrent Unit (BiGRU) architectures with attention mechanisms were used for both problems, and Siamese Manhattan Long Short-Term Memory (MaLSTM) architectures were used for question pair identification.…”

Section: Chandra and Stefanusmentioning

confidence: 99%

Enhancing Question Pairs Identification with Ensemble Learning: Integrating Machine Learning and Deep Learning Models

Tarek,

Noaman,

Kayed

2023

IJACSA

View full text Add to dashboard Cite

The effectiveness of machine learning (ML) and deep learning (DL) models on the Quora question pairs dataset is investigated in this study. ML models, including AdaBoost, reached 73.44% test accuracy, while ensemble learning approaches enhanced outcomes even further, with the Hard-Voting Ensemble achieving 76.13%. DL models, such as FCN, demonstrated test accuracy of 81% with cross validation. These findings contribute to natural language processing by demonstrating the potential of ensemble learning for ML models and the DL models' detailed pattern-capturing capacity.

show abstract

Section: Chandra and Stefanusmentioning

confidence: 99%