.png){kind=icon}
返回
User feedback based metasearching using neural network
.png){kind=icon}
PRE
AI
DOI：10.1007/s13042-013-0212-2.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Metasearch engines are the web services that receive user queries and dispatch them to multiple crawler based search engines. After this, they collect the returned search results, reorder them and present the reordered list to the end user. To combine the results from different search engines, a metasearch engine may use different rank aggregation techniques to aggregate the various rankings of the search results to generate an overall ranking. If different rank aggregation techniques are used to collate search results, the results of metasearching for the same query may vary for the same set of participating search engines. In this paper, we discuss a metasearching technique that utilizes neural network based rank aggregation. Here, we formulate the rank aggregation problem as a function approximation problem. As the multilayer perceptrons are considered universal approximators, we use a multilayer perceptron for rank aggregation. We compare the performance of the neural network based method with four other methods namely rough set based method, modified rough set based method, Borda's method and a Markov Chain based method (MC2) using three independent evaluators. Experimentally, we find that the neural network based method performs better than each of these four methods.
Keyword:
Metasearching
User feedback
Neural network
Correlation coefficient
Performance evaluation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
2.7
论文数:
3.2K
被引数:
5.6K
机构
引用论文
Exploring the Potential Hormonal Effects of Tire Polymers (TPs) on Different Species Based on a Theoretical Computational Approach.png)
Polymers
OAAI
PolymersIF0
OAAI分享收藏分享收藏Improving pattern discovery and visualisation with self-adaptive neural networks through data transformations通过数据转换使用自适应神经网络改进模式发现和可视化
PREAI
分享收藏
查看更多内容