“Hulan-2014-11-06”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
improve lucene search
Lr讨论 | 贡献
Spell mistake
第2行: 第2行:
 
==Algorithm==
 
==Algorithm==
 
===Spell mistake===
 
===Spell mistake===
:* retrain the ngram model  
+
:* retrain the ngram model(caoli)
 +
 
 
===improve lucene search===
 
===improve lucene search===
 
* our vsm method
 
* our vsm method

2014年11月6日 (四) 08:46的版本

Dialog system

Algorithm

Spell mistake

  • retrain the ngram model(caoli)

improve lucene search

  • our vsm method
different result in lucene
method lucene vsm_idf(haiguan) VSM_idf(baidu) vsm_idf(tain) vsm_idf(calculate)
Accary 0.6628 0.6228 0.6197 0.5827 0.5426
  • lucene top
  • top10(82.95%),top20(86.34),top50(90.23%),top100(94.11%),top200(96.18%),top1000(97.31%),top2000(97.87%),top5000(98.75%),top10000(99.06)
  • lucene Optimization(liurong)
  • rewrite the method to select the 50 standard question not same template.
  • check the word segment for template.
  • boost the query keyword using IDF
boost keyword in lucene
method Default idf_train idf_train_norm idf_baidu idf_baidu_norm
Accary 0.66228 0.651629 0.57644 0.647869 0.65288
  • using MERT-4 method to get good value of multi-feature.like IDF,NER,baidu_weight,keyword etc.

Multi-Scene Recognition

  • add the triples search to QA engine
  • discuss the detail and give a report.

knowledge structure

  • structure the default answer using attributes of the entity.

Knowledge Management and labeling system

  • prepare the interface and function.

plan to do

plan to discuss

  • add the triples search to QA engine