融合复制机制和input-feeding方法的中文自动摘要模型

Chinese automatic summarization model of combining copying mechanism and input-feeding approach

针对中文自动摘要准确率不高的问题,在含有注意力机制的序列到序列(sequence-to-sequence,seq2seq)基础模型的解码器中融合了复制机制和input-feeding方法,提出了准确率更高的中文自动摘要模型。首先,该模型使用指针网络将出现在源序列中的OOV(out-of-vocabulary)词扩展到固定词典,以实现从源序列复制OOV词到生成序列中;其次,input-feeding方法用于跟踪已生成序列的注意力决定信息以提升模型输出准确率。在NLPCC2018数据集上的实验结果表明,与基础模型相比,所提出模型获得了更高的ROUGE得分,验证了该模型的可行性。

This paper presented a novel model for the lower accuracy issue in Chinese automatic summary which merged copying mechanism and input-feeding approach into the decoder of sequence-to-sequence(seq2 seq) basic model with attention mechanism.Firstly,it used pointer networks to extend the source’s OOV words to a fixed dictionary to copy OOV words from the source into the generated sequence.Secondly,it used the input-feeding approach to track the attention decision information of generated sequence for improving the model output accuracy.Experimental results on NLPCC2018 datasets show that the proposed model obtains a higher ROUGE score than the basic model,which confirms the feasibility of this model.