arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2402.05976cs.LGcs.AI
收藏

RankSum:一种基于排名融合的无监督抽取式文本摘要方法

RankSum An unsupervised extractive text summarization based on rank fusion

Universidad de León(莱昂大学);INCIBE (Spanish National Cybersecurity Institute)(西班牙国家网络安全研究所(INCIBE));Centre for Development of Advanced Computing(先进计算发展中心)

A. Joshi, E. Fidalgo, E. Alegre, R. Alaiz-Rodriguez

AI总结:

本文提出RankSum,一种基于四种句子特征排名融合的无监督抽取式摘要方法,在CNN/DailyMail和DUC 2002数据集上优于现有最先进方法。

摘要:

在本文中,我们提出了Ranksum,一种针对单文档的抽取式文本摘要方法,该方法基于对每个句子提取的四个多维句子特征进行排名融合:主题信息、语义内容、显著关键词和位置。Ranksum以无监督方式获取每个特征对应的句子显著性排名,随后对这四种分数进行加权融合,以根据句子的重要性对其进行排序。这些分数完全以无监督方式生成,并且需要带标签的文档集来学习融合权重。由于我们发现融合权重可以泛化到其他数据集,因此我们将Ranksum视为一种无监督方法。为了确定主题排名,我们采用概率主题模型,而语义信息则通过句子嵌入来捕获。为了利用句子嵌入推导排名,我们使用孪生网络生成抽象式句子表示,然后制定一种新颖的策略来按重要性顺序排列它们。采用基于图的方法来识别文档中的显著关键词和相关句子排名。我们还基于二元组、三元组和句子嵌入制定了一种句子新颖性度量,以消除摘要中的冗余句子。最终,将每个特征计算出的所有句子排名进行融合,以获得文档中每个句子的最终分数。我们在公开可用的摘要数据集CNN/DailyMail和DUC 2002上评估了我们的方法。实验结果表明,我们的方法优于其他现有的最先进摘要方法。

英文摘要:

In this paper, we propose Ranksum, an approach for extractive text summarization of single documents based on the rank fusion of four multi-dimensional sentence features extracted for each sentence: topic information, semantic content, significant keywords, and position. The Ranksum obtains the sentence saliency rankings corresponding to each feature in an unsupervised way followed by the weighted fusion of the four scores to rank the sentences according to their significance. The scores are generated in completely unsupervised way, and a labeled document set is required to learn the fusion weights. Since we found that the fusion weights can generalize to other datasets, we consider the Ranksum as an unsupervised approach. To determine topic rank, we employ probabilistic topic models whereas semantic information is captured using sentence embeddings. To derive rankings using sentence embeddings, we utilize Siamese networks to produce abstractive sentence representation and then we formulate a novel strategy to arrange them in their order of importance. A graph-based strategy is applied to find the significant keywords and related sentence rankings in the document. We also formulate a sentence novelty measure based on bigrams, trigrams, and sentence embeddings to eliminate redundant sentences from the summary. The ranks of all the sentences computed for each feature are finally fused to get the final score for each sentence in the document. We evaluate our approach on publicly available summarization datasets CNN/DailyMail and DUC 2002. Experimental results show that our approach outperforms other existing state-of-the-art summarization methods.

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。

↑