Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features
Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features
复制标题
DOI：
10.18653/v1/w18-6536
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
Vrindavan Harrison;M. Walker
中科院分区：
文献类型：
--
作者：
Vrindavan Harrison;M. Walker
问题生成是从文本输入自动创建问题的任务。在这项工作中，我们提出了一个新的注意力编码器-解码器递归神经网络模型的自动生成问题。我们的模型结合了语言特征和额外的句子嵌入，以捕获句子和单词级别的含义。语言学特征被设计为捕获与命名实体识别、词的大小写和实体共指消解相关的信息。此外，我们的模型使用了一个复制机制和一个特殊的答案信号，使一个给定的句子生成许多不同的问题。我们的模型在基准问题生成数据集上实现了19.98 Bleu_4的最新结果，大大优于所有先前发表的结果。人工评估还表明，添加的功能提高了生成的问题的质量。
Question Generation is the task of automatically creating questions from textual input. In this work we present a new Attentional Encoder–Decoder Recurrent Neural Network model for automatic question generation. Our model incorporates linguistic features and an additional sentence embedding to capture meaning at both sentence and word levels. The linguistic features are designed to capture information related to named entity recognition, word case, and entity coreference resolution. In addition our model uses a copying mechanism and a special answer signal that enables generation of numerous diverse questions on a given sentence. Our model achieves state of the art results of 19.98 Bleu_4 on a benchmark Question Generation dataset, outperforming all previously published results by a significant margin. A human evaluation also shows that the added features improve the quality of the generated questions.