Neural Paraphrase Generation with Stacked Residual LSTM Networks

Abstract

In this paper, we propose a novel neural approach for paraphrase generation. Conventional para- phrase generation methods either leverage hand-written rules and thesauri-based alignments, or use statistical machine learning principles. To the best of our knowledge, this work is the first to explore deep learning models for paraphrase generation. Our primary contribution is a stacked residual LSTM network, where we add residual connections between LSTM layers. This allows for efficient training of deep LSTMs. We evaluate our model and other state-of-the-art deep learning models on three different datasets: PPDB, WikiAnswers and MSCOCO. Evaluation results demonstrate that our model outperforms sequence to sequence, attention-based and bi- directional LSTM models on BLEU, METEOR, TER and an embedding-based sentence similarity metric.

COLING 2016

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Sequence to Sequence Learning with Neural Networks
• Skip-Thought Vectors
• Show and Tell: A Neural Image Caption Generator

Cited by in corpus (19)

• Unsupervised Paraphrase Generation using Pre-trained Language Models
• Simulated annealing for optimization of graphs and sequences
• Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention
• Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach
• Zero-Shot Paraphrase Generation with Multilingual Language Models
• Neural Poetry: Learning to Generate Poems using Syllables
• Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning
• Controllable Paraphrase Generation with a Syntactic Exemplar
• Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs
• Syntax-Infused Variational Autoencoder for Text Generation
• Diversifying Task-oriented Dialogue Response Generation with Prototype Guided Paraphrasing
• PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction
• MAPGN: MAsked Pointer-Generator Network for sequence-to-sequence pre-training
• Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering
• Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation
• Modality Compensation Network: Cross-Modal Adaptation for Action Recognition
• Delexicalized Paraphrase Generation
• Learning to Selectively Learn for Weakly-supervised Paraphrase Generation
• Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs