arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.13136cs.IR
收藏

多层文本摘要模型对基于向量空间的信息检索效率和相关性的影响

The Effect of the Multi-Layer Text Summarization Model on the Efficiency and Relevancy of the Vector Space-based Information Retrieval

Ahmad Hussein Ababneh, Joan Lu, Qiang Xu

摘要:

互联网上的大量上传文本在信息检索系统中产生了巨大的倒排索引,这损害了它们的效率。本研究的目的是衡量自动摘要的多层相似度模型在建立信息量大、简洁的倒排索引方面的效果。为了实现这一目的,我们总结了相当数量的文档使用多层相似性模型,我们建立了倒排索引从自动摘要,从这个模型产生的。一系列的实验进行了测试的效率和相关性方面的性能。实验包括与三个现有的文本摘要模型的比较; Jaccard系数模型,向量空间模型,和潜在语义分析模型。实验研究了三组查询与手动和自动相关性评估。多层相似性在IR系统的效率中的积极作用是明显的,而相关性结果没有明显的损失。然而,评估表明,传统的统计模型没有语义调查未能提高信息检索的效率。与以前的出版物,解决了使用摘要作为索引的来源,我们的工作的相关性评估更高,和多层相似性检索构建的倒排索引是58%小于主语料倒排索引。

英文摘要:

The massive upload of text on the internet creates a huge inverted index in information retrieval systems, which hurts their efficiency. The purpose of this research is to measure the effect of the Multi-Layer Similarity model of the automatic text summarization on building an informative and condensed invert index in the IR systems. To achieve this purpose, we summarized a considerable number of documents using the Multi-Layer Similarity model, and we built the inverted index from the automatic summaries that were generated from this model. A series of experiments were held to test the performance in terms of efficiency and relevancy. The experiments include comparisons with three existing text summarization models; the Jaccard Coefficient Model, the Vector Space Model, and the Latent Semantic Analysis model. The experiments examined three groups of queries with manual and automatic relevancy assessment. The positive effect of the Multi-Layer Similarity in the efficiency of the IR system was clear without noticeable loss in the relevancy results. However, the evaluation showed that the traditional statistical models without semantic investigation failed to improve the information retrieval efficiency. Comparing with the previous publications that addressed the use of summaries as a source of the index, the relevancy assessment of our work was higher, and the Multi-Layer Similarity retrieval constructed an inverted index that was 58% smaller than the main corpus inverted index.

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。

↑