Exploring events and distributed representations of text in multi-document summarization
Exploring events and distributed representations of text in multi-document summarization
复制标题
DOI：
10.1016/j.knosys.2015.11.005
复制
发表时间：
2016-02-15
影响因子：
8.8
通讯作者：
Neto, Joao P.
中科院分区：
文献类型：
--
作者：
Marujo, Luis;Ling, Wang;Neto, Joao P.
在本文中，我们探索了一个事件检测框架来改进多文档摘要。我们的方法基于两阶段的单文档方法，该方法提取关键短语的集合，然后将其用于中心即相关性段落检索模型。我们将探索如何将这种单文档方法应用于能够使用事件信息的多文档摘要方法。事件检测方法基于模糊指纹，这是一种对带有注释事件标签的文档进行训练的监督方法。为了应对可能使用不同术语来描述同一事件的情况，我们探索了以词嵌入的形式对文本进行分布式表示，这有助于提高摘要结果。所提出的摘要方法基于单文档摘要的分层组合。在DUC 2007和TAC 2009两个主流评估数据集上进行的自动评估和人类研究表明，这些方法改进了当前最先进的多文档摘要系统。我们显示，2009年TAC的ROUGE-1分数相对提高了16%，2007年DUC的则提高了17%。(C) 2015年Elsevier B.V.出版
In this article, we explore an event detection framework to improve multi-document summarization. Our approach is based on a two-stage single-document method that extracts a collection of key phrases, which are then used in a centrality-as-relevance passage retrieval model. We explore how to adapt this single document method for multi-document summarization methods that are able to use event information. The event detection method is based on Fuzzy Fingerprint, which is a supervised method trained on documents with annotated event tags. To cope with the possible usage of different terms to describe the same event, we explore distributed representations of text in the form of word embeddings, which contributed to improve the summarization results. The proposed summarization methods are based on the hierarchical combination of single-document summaries. The automatic evaluation and human study performed show that these methods improve upon current state-of-the-art multi-document summarization systems on two mainstream evaluation datasets, DUC 2007 and TAC 2009. We show a relative improvement in ROUGE-1 scores of 16% for TAC 2009 and of 17% for DUC 2007. (C) 2015 Published by Elsevier B.V.