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

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.

References in corpus (9)

• Distributed Representations of Words and Phrases and their Compositionality
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features
• Sentence Similarity Learning by Lexical Decomposition and Composition
• A Deep Network Model for Paraphrase Detection in Short Text Messages
• Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering
• A Multi-cascaded Deep Model for Bilingual SMS Classification
• Kernel functions based on triplet comparisons

Cited by in corpus (7)

• Data Augmentation Approaches in Natural Language Processing: A Survey
• Predicting Attributes of Nodes Using Network Structure
• An enhanced Tree-LSTM architecture for sentence semantic modeling using typed dependencies
• Extracting Problem and Method Sentence from Scientific Papers: A Context-enhanced Transformer Using Formulaic Expression Desensitization
• BET: A Backtranslation Approach for Easy Data Augmentation in Transformer-based Paraphrase Identification Context
• The power of text similarity in identifying AI-LLM paraphrased documents: The case of BBC news articles and ChatGPT
• Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory