A Multi-cascaded Model with Data Augmentation for Enhanced Paraphrase Detection in Short Texts

TL;DR

This paper introduces a novel data augmentation method and a multi-cascaded deep learning model to improve paraphrase detection in short texts, achieving state-of-the-art results on benchmark datasets.

Contribution

It presents a graph-based data augmentation strategy combined with a multi-cascaded CNN-LSTM model for more effective paraphrase detection in short texts.

Findings

Achieves state-of-the-art performance on three benchmark datasets.

Demonstrates robustness across clean and noisy short texts.

Enhances paraphrase detection accuracy with combined deep and hand-crafted features.

Abstract

Paraphrase detection is an important task in text analytics with numerous applications such as plagiarism detection, duplicate question identification, and enhanced customer support helpdesks. Deep models have been proposed for representing and classifying paraphrases. These models, however, require large quantities of human-labeled data, which is expensive to obtain. In this work, we present a data augmentation strategy and a multi-cascaded model for improved paraphrase detection in short texts. Our data augmentation strategy considers the notions of paraphrases and non-paraphrases as binary relations over the set of texts. Subsequently, it uses graph theoretic concepts to efficiently generate additional paraphrase and non-paraphrase pairs in a sound manner. Our multi-cascaded model employs three supervised feature learners (cascades) based on CNN and LSTM networks with and without soft-attention. The learned features, together with hand-crafted linguistic features, are then forwarded to a discriminator network for final classification. Our model is both wide and deep and provides greater robustness across clean and noisy short texts. We evaluate our approach on three benchmark datasets and show that it produces a comparable or state-of-the-art performance on all three.