Abstractive Document Summarization via Neural Model with Joint Attention

扫码查看

原文链接

NETL
Springer Nature

外文摘要：Due to the difficulty of abstractive summarization， the great majority of past work on document summarization has been extractive， while the recent success of sequence-to-sequence framework has made abstractive summarization viable， in which a set of recurrent neural networks models based on attention encoder-decoder have achieved promising performance on short-text summarization tasks。 Unfortunately， these attention encoder-decoder models often suffer from the undesirable shortcomings of generating repeated words or phrases and inability to deal with out-of-vocabulary words appropriately。 To address these issues， in this work we propose to add an attention mechanism on output sequence to avoid repetitive contents and use the subword method to deal with the rare and unknown words。 We applied our model to the public dataset provided by NLPCC 2017 shared task3。 The evaluation results show that our system achieved the best ROUGE performance among all the participating teams and is also competitive with some state-of-the-art methods。

外文关键词：

Abstractive summarizationAttentional mechanism Encoder-decoder frameworkNeural network

作者：

Liwei Hou、Po Hu、Chao Bei

展开 >

作者单位：

School of Computer Science, Central China Normal University, Wuhan 430079, China

Global Tone Communication Technology Co., Ltd., Beijing 100043, China

会议名称：

CCF international conference on natural language processing and Chinese computing

会议地点：

Dalian(CN)

会议母体文献：

Natural language understanding and intelligent applications

页码：

329-338

出版时间：

2017

DOI：

10.1007/978-3-319-73618-1_28