Combining word embeddings and convolutional neural networks to detect duplicated questions

TL;DR

This paper presents a method combining word embeddings and CNNs to detect semantically similar questions, demonstrating effectiveness on the Quora dataset and exploring various embedding techniques for improved performance.

Contribution

It introduces a simple approach that integrates word embeddings with CNNs for question similarity detection and evaluates multiple embedding methods on a large dataset.

Findings

The model achieves competitive results on Quora dataset.

Cosine similarity effectively compares feature vectors.

Different embeddings impact model performance.

Abstract

Detecting semantic similarities between sentences is still a challenge today due to the ambiguity of natural languages. In this work, we propose a simple approach to identifying semantically similar questions by combining the strengths of word embeddings and Convolutional Neural Networks (CNNs). In addition, we demonstrate how the cosine similarity metric can be used to effectively compare feature vectors. Our network is trained on the Quora dataset, which contains over 400k question pairs. We experiment with different embedding approaches such as Word2Vec, Fasttext, and Doc2Vec and investigate the effects these approaches have on model performance. Our model achieves competitive results on the Quora dataset and complements the well-established evidence that CNNs can be utilized for paraphrase detection tasks.