Combining word embeddings and convolutional neural networks to detect duplicated questions

2020/06/08 by Yoan Dimitrov, Dimitrov, Yoan
Computer Science · #Topic Modeling #Software Engineering Research #Spam and Phishing Detection

paper · pdf · doi:10.48550/arxiv.2006.04513

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.

Citations

• A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification

Related

• Contextualized Embeddings based Convolutional Neural Networks for Duplicate Question Identification
• Identifying Semantically Duplicate Questions Using Data Science Approach: A Quora Case Study
• Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering
• Better Early than Late: Fusing Topics with Word Embeddings for Neural Question Paraphrase Identification
• Sentence Modeling via Multiple Word Embeddings and Multi-level Comparison for Semantic Textual Similarity