“Hulan-2015-02-06”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以“=Dialog system= ==Algorithm== ===Spell mistake=== :* done ===improve fuzzy match=== * hold ===improve lucene search=== * learning to rank [http://cslt.riit.tsinghua....”为内容创建页面)
 
Lr讨论 | 贡献
reverse module
 
(相同用户的一个中间修订版本未显示)
第12行: 第12行:
 
===Online Learning===
 
===Online Learning===
 
* begin to set.
 
* begin to set.
 +
* solution(tianyi will give a solution)
 +
:* add index when the user give positive reaction
 +
:* add query distribution to boost weight
 +
:* using recommend list to boost the weight
 +
 
===reverse module===
 
===reverse module===
 
* knowledge graph  
 
* knowledge graph  
 
:* process of setting knowledge graph and support reverse ask[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/18/%E6%94%BF%E5%BA%9C%E7%BB%84%E7%BB%87%E6%9C%BA%E6%9E%84%E5%9B%BE%E8%B0%B1--%E6%B1%87%E8%81%94.pdf]
 
:* process of setting knowledge graph and support reverse ask[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/18/%E6%94%BF%E5%BA%9C%E7%BB%84%E7%BB%87%E6%9C%BA%E6%9E%84%E5%9B%BE%E8%B0%B1--%E6%B1%87%E8%81%94.pdf]
 
:* search the opensource jena and D2R
 
:* search the opensource jena and D2R
 +
:* give a demo
  
 
==Knowledge Management and labeling system==
 
==Knowledge Management and labeling system==

2015年2月8日 (日) 05:14的最后版本

Dialog system

Algorithm

Spell mistake

  • done

improve fuzzy match

  • hold

improve lucene search

  • learning to rank [1]
  • result: 0.688->0.78

Multi-Scene Recognition

  • demo (done)

Online Learning

  • begin to set.
  • solution(tianyi will give a solution)
  • add index when the user give positive reaction
  • add query distribution to boost weight
  • using recommend list to boost the weight

reverse module

  • knowledge graph
  • process of setting knowledge graph and support reverse ask[2]
  • search the opensource jena and D2R
  • give a demo

Knowledge Management and labeling system

  • continue coding.

Patent

  • done

new word find

  • done