arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.08748cs.CL
收藏

DynE:多文档摘要的动态加密解码

DynE: Dynamic Ensemble Decoding for Multi-Document Summarization

Aylien Ltd.(Aylien有限公司);Insight Centre for Data Analytics(洞察数据分析中心);University College Dublin(都柏林大学学院)

Chris Hokamp, Demian Gholipour Ghalandari, Nghia The Pham, John Glover

摘要:

序列到序列(s2 s)模型是自然语言处理中广泛工作的基础。然而,某些应用,例如多文档摘要、多模态机器翻译和机器翻译的自动后期编辑,需要将多个不同输入的集合映射到单个输出序列中。最近的工作已经为这些多输入设置引入了定制的架构,并开发了可以处理越来越长的输入的模型;然而,特殊模型架构的性能受到可用的域内训练数据的限制。在这项工作中,我们提出了一个简单的解码方法,它集成了不同的输入相同的模型的多个实例的输出。我们提出的方法允许为vanilla s2 s任务训练的模型直接用于多输入设置。当每个输入都与其他输入有显著重叠时,这种方法特别有效,例如将关于同一事件的一组新闻文章压缩成单个连贯摘要时,我们在几个多文档摘要数据集上获得了最先进的结果。

英文摘要:

Sequence-to-sequence (s2s) models are the basis for extensive work in natural language processing. However, some applications, such as multi-document summarization, multi-modal machine translation, and the automatic post-editing of machine translation, require mapping a set of multiple distinct inputs into a single output sequence. Recent work has introduced bespoke architectures for these multi-input settings, and developed models which can handle increasingly longer inputs; however, the performance of special model architectures is limited by the available in-domain training data. In this work we propose a simple decoding methodology which ensembles the output of multiple instances of the same model on different inputs. Our proposed approach allows models trained for vanilla s2s tasks to be directly used in multi-input settings. This works particularly well when each of the inputs has significant overlap with the others, as when compressing a cluster of news articles about the same event into a single coherent summary, and we obtain state-of-the-art results on several multi-document summarization datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑