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 1809.02393cs.CLcs.AIcs.NE
收藏

使用答案分离改进神经问题生成

Improving Neural Question Generation using Answer Separation

Seoul National University(首尔国立大学);Automation and Systems Research Institute, Seoul National University(首尔国立大学自动化与系统研究所)

Yanghoon Kim, Hwanhee Lee, Joongbo Shin, Kyomin Jung

摘要:

神经问题生成(NQG)是利用深度神经网络从给定段落生成问题的任务。以前的NQG模型存在一个问题,即生成的问题中有很大一部分包括问题目标中的单词,从而导致生成非预期的问题。在本文中,我们提出了答案分离seq2seq,它更好地利用了信息,从通道和目标答案。通过用特殊的标记替换原始段落中的目标答案,我们的模型学习识别应该使用哪个疑问词。我们还提出了一个新的模块称为关键词网,它有助于模型更好地捕捉目标答案中的关键信息,并生成适当的问题。实验结果表明,我们的答案分离方法显着减少了不适当的问题,其中包括答案的数量。因此,我们的模型显着优于以前的国家的最先进的NQG模型。

英文摘要:

Neural question generation (NQG) is the task of generating a question from a given passage with deep neural networks. Previous NQG models suffer from a problem that a significant proportion of the generated questions include words in the question target, resulting in the generation of unintended questions. In this paper, we propose answer-separated seq2seq, which better utilizes the information from both the passage and the target answer. By replacing the target answer in the original passage with a special token, our model learns to identify which interrogative word should be used. We also propose a new module termed keyword-net, which helps the model better capture the key information in the target answer and generate an appropriate question. Experimental results demonstrate that our answer separation method significantly reduces the number of improper questions which include answers. Consequently, our model significantly outperforms previous state-of-the-art NQG models.

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。

↑