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

arXiv: https://arxiv.org/abs/1912.12068 · HTML: https://mlsanity.com/paper/1912.12068/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Dec 2019.

## Built on by (most cited first, 11 of 11)

- [Data Augmentation Approaches in Natural Language Processing: A Survey](https://mlsanity.com/paper/2110.01852/) (2021)
- [Spike2Vec: An Efficient and Scalable Embedding Approach for COVID-19 Spike Sequences](https://mlsanity.com/paper/2109.05019/) (2021)
- [A k-mer Based Approach for SARS-CoV-2 Variant Identification](https://mlsanity.com/paper/2108.03465/) (2021)
- [Effective and scalable clustering of SARS-CoV-2 sequences](https://mlsanity.com/paper/2108.08143/) (2021)
- [Robust Representation and Efficient Feature Selection Allows for Effective Clustering of SARS-CoV-2 Variants](https://mlsanity.com/paper/2110.09622/) (2021)
- [Efficient Analysis of COVID-19 Clinical Data using Machine Learning Models](https://mlsanity.com/paper/2110.09606/) (2021)
- [Computing Graph Descriptors on Edge Streams](https://mlsanity.com/paper/2109.01494/) (2021)
- [Characterizing SARS-CoV-2 Spike Sequences Based on Geographical Location](https://mlsanity.com/paper/2110.00809/) (2021)
- [Information We Can Extract About a User From 'One Minute Mobile Application Usage'](https://mlsanity.com/paper/2207.13222/) (2022)
- [The power of text similarity in identifying AI-LLM paraphrased documents: The case of BBC news articles and ChatGPT](https://mlsanity.com/paper/2505.12405/) (2025)
- [Extracting Problem and Method Sentence from Scientific Papers: A Context-enhanced Transformer Using Formulaic Expression Desensitization](https://mlsanity.com/paper/2606.26481/) (2026)

## Abstract (arXiv)

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.