Neural Paraphrase Generation with Stacked Residual LSTM Networks

摘要

In this paper, we propose a novel neural approach for paraphrase generation. Conventional paraphrase 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 datascts: PPDB, WikiAnswers, and MSCOCO. Evaluation results demonstrate that our model outperforms sequence to sequence, attention-based, and bidirectional LSTM models on BLEU, METEOR, TER, and an embedding-based sentence similarity metric.