Chali, Yllias, and Rafat Islam. "Question-question similarity in online forums." Proceedings of the 10th annual meeting of the forum for information retrieval evaluation. 2018.

This paper explores the use of deep learning frameworks for detecting duplicate questions using a siamese architecture with Long Short-Term Memory (LSTM) and Bi-directional LSTM (biLSTM) networks. The study extends basic models with Convolutional Neural Networks (CNNs) and attention mechanisms to enhance semantic similarity detection between questions. Trained on a large-scale dataset of 400,000 labeled question pairs from Quora, the models achieved notable improvements in accuracy, precision, recall, and F1 scores compared to baseline and state-of-the-art systems.