<?xml version="1.0"?>
<?xml-stylesheet type="text/css" href="http://cslt.org/mediawiki/skins/common/feed.css?303"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="zh-cn">
		<id>http://cslt.org/mediawiki/index.php?action=history&amp;feed=atom&amp;title=Zhongda_Xie_15-05-25</id>
		<title>Zhongda Xie 15-05-25 - 版本历史</title>
		<link rel="self" type="application/atom+xml" href="http://cslt.org/mediawiki/index.php?action=history&amp;feed=atom&amp;title=Zhongda_Xie_15-05-25"/>
		<link rel="alternate" type="text/html" href="http://cslt.org/mediawiki/index.php?title=Zhongda_Xie_15-05-25&amp;action=history"/>
		<updated>2026-04-10T11:20:19Z</updated>
		<subtitle>本wiki的该页面的版本历史</subtitle>
		<generator>MediaWiki 1.23.3</generator>

	<entry>
		<id>http://cslt.org/mediawiki/index.php?title=Zhongda_Xie_15-05-25&amp;diff=15273&amp;oldid=prev</id>
		<title>Xiezd：以“Progress in Last Week:  Start for a new work: Detecting key entity in a query.  (e.g. In query &quot;pickup for guitar&quot;, the key entity is &quot;pickup&quot;.)  Plan: (1)Use web se...”为内容创建页面</title>
		<link rel="alternate" type="text/html" href="http://cslt.org/mediawiki/index.php?title=Zhongda_Xie_15-05-25&amp;diff=15273&amp;oldid=prev"/>
				<updated>2015-05-31T11:21:05Z</updated>
		
		<summary type="html">&lt;p&gt;以“Progress in Last Week:  Start for a new work: Detecting key entity in a query.  (e.g. In query &amp;quot;pickup for guitar&amp;quot;, the key entity is &amp;quot;pickup&amp;quot;.)  Plan: (1)Use web se...”为内容创建页面&lt;/p&gt;
&lt;p&gt;&lt;b&gt;新页面&lt;/b&gt;&lt;/p&gt;&lt;div&gt;Progress in Last Week:&lt;br /&gt;
&lt;br /&gt;
Start for a new work: Detecting key entity in a query.&lt;br /&gt;
&lt;br /&gt;
(e.g. In query &amp;quot;pickup for guitar&amp;quot;, the key entity is &amp;quot;pickup&amp;quot;.)&lt;br /&gt;
&lt;br /&gt;
Plan: (1)Use web search co-click data to obtain training data, use query pair to determine key entity.&lt;br /&gt;
&lt;br /&gt;
(2)for each query, extract the following information: stemmed word, POS, entity, modifier and so on.&lt;br /&gt;
&lt;br /&gt;
(3)Use CRF model to learn from training data, using features that are extracted in step (2); finally predict key entity in unseen queries.&lt;/div&gt;</summary>
		<author><name>Xiezd</name></author>	</entry>

	</feed>