http://www.cslt.org/mediawiki/index.php?action=history&feed=atom&title=Zhongda_Xie_14-12-01Zhongda Xie 14-12-01 - 版本历史2026-04-04T22:56:06Z本wiki的该页面的版本历史MediaWiki 1.23.3http://www.cslt.org/mediawiki/index.php?title=Zhongda_Xie_14-12-01&diff=12809&oldid=prevXiezd：以“Progress in Last Week: (1)Use the Dictionary to transform SenticNet English entries into Chinese terms. (2)Use HIT wordNet to map the Chinese terms to HIT-wordNet...”为内容创建页面2014-12-01T11:54:24Z<p>以“Progress in Last Week: (1)Use the Dictionary to transform SenticNet English entries into Chinese terms. (2)Use HIT wordNet to map the Chinese terms to HIT-wordNet...”为内容创建页面</p>
<p><b>新页面</b></p><div>Progress in Last Week:<br />
<br />
(1)Use the Dictionary to transform SenticNet English entries into Chinese terms.<br />
<br />
(2)Use HIT wordNet to map the Chinese terms to HIT-wordNet Concepts.<br />
<br />
(3)In our text collection, we search sentences including the instance keywords of the Concepts in (2).<br />
<br />
Plan for This Week:<br />
<br />
For each concept, We already have relevant sentences, Run LDA on these sentences.<br />
<br />
Each topic of the LDA result is considered as the a sense of the concept, and it is taken as the entry in Chinese-SenticNet.<br />
<br />
Each entry should have five terms, which often co-occur with the entry concept, and these are extracted from the LDA result--- the most relevant words to the topic.</div>Xiezd