arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.05074cs.CL
收藏

一个用于释义生成的深度生成框架

A Deep Generative Framework for Paraphrase Generation

IBM

Ankush Gupta, Arvind Agarwal, Prawaan Singh, Piyush Rai

摘要:

释义生成是自然语言处理中的一个重要问题,特别是在问答、信息检索、信息抽取、会话系统等领域。在本文中,我们解决自动生成释义的问题。我们提出的方法是基于深度生成模型(VAE)与序列到序列模型(LSTM)的组合,在给定输入句子的情况下生成释义。传统的VAE与递归神经网络相结合时,可以生成自由文本,但它们不适合用于给定句子的释义生成。我们解决这个问题的条件,编码器和解码器端的VAE,对原始的句子,使它可以生成给定的句子的释义。与大多数现有的模型不同,我们的模型是简单的,模块化的,可以生成多个释义,为一个给定的句子。在基准释义数据集上对所提出的方法进行的定量评估表明了其有效性,并且其性能比最先进的方法有显著的提高,而定性的人类评估表明生成的释义格式良好,语法正确,并且与输入句子相关。此外,我们评估我们的方法在一个新发布的问题释义数据集,并建立一个新的基线为未来的研究。

英文摘要:

Paraphrase generation is an important problem in NLP, especially in question answering, information retrieval, information extraction, conversation systems, to name a few. In this paper, we address the problem of generating paraphrases automatically. Our proposed method is based on a combination of deep generative models (VAE) with sequence-to-sequence models (LSTM) to generate paraphrases, given an input sentence. Traditional VAEs when combined with recurrent neural networks can generate free text but they are not suitable for paraphrase generation for a given sentence. We address this problem by conditioning the both, encoder and decoder sides of VAE, on the original sentence, so that it can generate the given sentence's paraphrases. Unlike most existing models, our model is simple, modular and can generate multiple paraphrases, for a given sentence. Quantitative evaluation of the proposed method on a benchmark paraphrase dataset demonstrates its efficacy, and its performance improvement over the state-of-the-art methods by a significant margin, whereas qualitative human evaluation indicate that the generated paraphrases are well-formed, grammatically correct, and are relevant to the input sentence. Furthermore, we evaluate our method on a newly released question paraphrase dataset, and establish a new baseline for future research.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑