[SearchEngine]text summarizer技术

Kevin的工具：Tailrank text summarizer，是展示language categorization and text summarizer technology的，也就是说，他搜索你提供的blog永久连接时，就可以解析出何种语言，以及自动提炼出blog的概述(summarizer)。

我到http://tools.tailrank.com/上试验了一把，比如提供这么一个地址：

http://weblogs.java.net/blog/tomwhite/archive/2005/09/mapreduce.html

Tailrank解析的结果是：

Resulting Summary

summary:

NDFS provides a fault-tolerant environment for working with very large files using cheap commodity hardware. This processing model is ideal for the operations a search engine indexer like Nutch or Google needs to perform - like computing inlinks for URLs, or building inverted indexes - and it will transform Nutch into a scalable, distributed search engine. Currently MapReduce is a part of Nutch, but it has been proposed that it and NDFS be moved into a separate project.

title: Tom White's Blog

lang: en

当然，第一提炼得不准，第二很多blog url都不能算出来。

Trackback: http://tb.blog.csdn.net/TrackBack.aspx?PostId=605933