Skip to main content

Table 6 Automatic word alignment results from batch 5

From: Creating a medical dictionary using word alignment: The influence of sources and resources

Batch

Run

Resources

Alignment

Result

  

Static

Statistic

Dynamic

          
  

Stan

POS

MeSH

Statistic partition

Training partition

Test partition

Recall

Precision

F-score

     

2

3

4

5

6

7

8

2

3

4

5

6

7

8

2

3

4

5

6

7

8

   

5

1

   

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

0.80

0.77

0.78

5

2

  

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

0.80

0.76

0.78

5

3

 

X

 

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

0.81

0.77

0.79

5

4

 

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

0.81

0.77

0.79

5

5

X

  

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

0.81

0.76

0.78

5

6

X

 

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

0.81

0.77

0.79

5

7

X

X

 

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

0.81

0.77

0.79

5

8

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

X

0.81

0.77

0.79

  1. Recall, precision and F-score from the automatic word alignment when resources for the automatic word alignment were generated from all partitions and all partitions were automatically aligned. If the standard resources, the parts-of-speech blocker and the MeSH-dictionary were used or not were instead altered in the 8 possible ways.
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us