arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1908.04942cs.CL
收藏

基于强化学习的图-序列自然问题生成模型

Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation

Rensselaer Polytechnic Institute(伦斯勒理工学院);IBM Research(IBM研究院)

Yu Chen, Lingfei Wu, Mohammed J. Zaki

摘要:

自然问题生成(Natural Question Generation,QG)的目的是从文章和答案中生成问题。以往的QG工作要么(i)忽略隐藏在文本中的丰富结构信息,(ii)仅仅依赖于交叉熵损失,导致暴露偏差和训练/测试测量之间的不一致等问题,或者(iii)未能充分利用答案信息。为了解决这些局限性,在本文中,我们提出了一个基于强化学习(RL)的图到序列(Graph 2Seq)模型QG。我们的模型由一个Graph 2Seq生成器和一个新的基于双向门控图神经网络的编码器组成,以嵌入通道,以及一个混合评估器,其混合目标结合了交叉熵和RL损失,以确保生成语法和语义有效的文本。我们还引入了一个有效的深度对齐网络,用于在单词和上下文两个层面将答案信息纳入文章中。我们的模型是端到端可训练的,并实现了新的最先进的分数,在标准SQuAD基准测试中显著优于现有方法。

英文摘要:

Natural question generation (QG) aims to generate questions from a passage and an answer. Previous works on QG either (i) ignore the rich structure information hidden in text, (ii) solely rely on cross-entropy loss that leads to issues like exposure bias and inconsistency between train/test measurement, or (iii) fail to fully exploit the answer information. To address these limitations, in this paper, we propose a reinforcement learning (RL) based graph-to-sequence (Graph2Seq) model for QG. Our model consists of a Graph2Seq generator with a novel Bidirectional Gated Graph Neural Network based encoder to embed the passage, and a hybrid evaluator with a mixed objective combining both cross-entropy and RL losses to ensure the generation of syntactically and semantically valid text. We also introduce an effective Deep Alignment Network for incorporating the answer information into the passage at both the word and contextual levels. Our model is end-to-end trainable and achieves new state-of-the-art scores, outperforming existing methods by a significant margin on the standard SQuAD benchmark.

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。

↑