其实就是基于这样的搜索引擎的:去掉无信息的词,然后从普通搜索引擎的结果中提取答案



所有跟贴·加跟贴·新语丝科技论坛

送交者: Roboo 于 2005-10-28, 00:09:53:

回答: 也许这些例子不错。也许我对自然语言处理的进展太悲观 由 AA 于 2005-10-27, 22:41:01:

I did many tests and found it used another popular search engine's results (move mouse over their results and see the URL in IE's status bar indicates redirect). So I got this conclusion.

I am not a full beliver of NLP, but I think borrowing some ideas can bring some improvement. For example, if you extract just locations and time and people's names etc. from Web pages, it will help people to search that page for such information. It will be better than simple word matching. A little NLP is achievable in reality, I think.



所有跟贴:


加跟贴

笔名: 密码(可选项): 注册笔名请按这里

标题:

内容(可选项):

URL(可选项):
URL标题(可选项):
图像(可选项):


所有跟贴·加跟贴·新语丝科技论坛