Guiding Generation for Abstractive Text Summarization Based on Key Information Guide Network
Guiding Generation for Abstractive Text Summarization Based on Key Information Guide Network
复制标题
DOI：
10.18653/v1/n18-2009
复制
发表时间：
2018-06
期刊：
影响因子：
--
通讯作者：
Chenliang Li;Chenliang Li;Weiran Xu;Si Li;Sheng Gao
中科院分区：
文献类型：
--
作者：
Chenliang Li;Chenliang Li;Weiran Xu;Si Li;Sheng Gao
神经网络模型建立在注意编解模型的基础上，具有较好的摘要性能。然而，这些模型在生成过程中很难控制，导致关键信息的缺乏。我们提出了一种抽象法和抽象法相结合的引导式生成模型。首先，我们通过抽取模型从文本中获取关键词。然后，我们引入了一个关键字信息指导网(Kign)，它将关键字编码成关键字信息表示，以指导生成过程。此外，我们还使用了一种预测-指导机制，可以为未来的解码获得长期价值，以进一步指导摘要的生成。我们在CNN/Daily Mail的数据集上对我们的模型进行了评估。实验结果表明，我们的模型有明显的改进。
Neural network models, based on the attentional encoder-decoder model, have good capability in abstractive text summarization. However, these models are hard to be controlled in the process of generation, which leads to a lack of key information. We propose a guiding generation model that combines the extractive method and the abstractive method. Firstly, we obtain keywords from the text by a extractive model. Then, we introduce a Key Information Guide Network (KIGN), which encodes the keywords to the key information representation, to guide the process of generation. In addition, we use a prediction-guide mechanism, which can obtain the long-term value for future decoding, to further guide the summary generation. We evaluate our model on the CNN/Daily Mail dataset. The experimental results show that our model leads to significant improvements.