Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation
Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representation
复制标题
DOI：
10.18653/v1/d18-1086
复制
发表时间：
2018-08
期刊：
影响因子：
--
通讯作者：
Hardy Hardy-Hardy;Andreas Vlachos
中科院分区：
文献类型：
--
作者：
Hardy Hardy-Hardy;Andreas Vlachos
最近关于抽象摘要的工作在神经编码器-解码器架构方面取得了进展。然而，这样的模型往往是挑战，由于他们缺乏明确的语义建模的源文档及其摘要。在本文中，我们使用抽象意义表示（AMR）与神经语言生成阶段，我们指导使用源文件的抽象摘要扩展以前的工作。我们证明，这一指导提高了7.4和10.5点，在ROUGE-2使用黄金标准AMR解析和解析从现成的解析器分别获得的摘要结果。我们还发现，后期解析的摘要性能比在较大数据集上训练的成熟神经编码器-解码器方法高2个ROUGE-2点。
Recent work on abstractive summarization has made progress with neural encoder-decoder architectures. However, such models are often challenged due to their lack of explicit semantic modeling of the source document and its summary. In this paper, we extend previous work on abstractive summarization using Abstract Meaning Representation (AMR) with a neural language generation stage which we guide using the source document. We demonstrate that this guidance improves summarization results by 7.4 and 10.5 points in ROUGE-2 using gold standard AMR parses and parses obtained from an off-the-shelf parser respectively. We also find that the summarization performance on later parses is 2 ROUGE-2 points higher than that of a well-established neural encoder-decoder approach trained on a larger dataset.