通过N-gram增强局部上下文视野感知的中文生成式摘要

基于序列到序列模型的生成式文档摘要算法已经取得了良好的效果。鉴于中文N-gram蕴含着丰富的局部上下文信息,该文提出将N-gram信息整合到现有模型的神经框架NgramSum,即利用N-gram信息增强神经模型局部上下文语义感知能力。该框架以现有的神经模型为主干,从本地语料库提取N-gram信息,提出了一个局部上下文视野感知增强模块和一个门模块,并来分别对这些信息进行编码和聚合。在NLPCC 2017中文单文档摘要评测数据集上的实验结果表明: 该框架有效增强了基于LSTM、Transformer、预训练模型三种不同层次的序列到序列的强基线模型,其中ROUGE-1/2/L相较基线模型平均分别提高了2.76, 3.25, 3.10个百分点。进一步的实验和分析也证明了该框架在不同N-gram度量方面的鲁棒性。

Chinese Abstractivte Summarization with Local Context Augmentation via N-gram

The abstractive document summarization algorithm based on sequence-to-sequence model has achieved good performance. Given that the rich local contextual information contained in Chinese n-grams, this paper proposes NgramSum to integrate n-gram information into the neural framework of the existing model.. The framework takes the existing neural model as the backbone, extracts n-grams information from the local corpus, and applies the n-gram information to augment the local context via a gate module. The experimental results on the dataset of NLPCC2017 shared task3 show that the framework effectively enhances the sequence-to-sequence strong baseline model of LSTM, Transformer, and pre-trained model with an average of 2.76%, 3.25% and 3.10% increase, respectively, according to the ROUGE-1/2/L scores.