pinyomi / eval /

Filename Size Date modified Message
933 B
221 B
7.9 KB
6.4 KB
3.5 KB
6.1 KB
1.1 KB
4.8 KB
15.7 KB
4.6 KB
3.5 KB
1.4 KB
24.7 KB
Process for evaluating Pinyomi


The evaluation is going to include two part


In reading experiment, the user will be asked to give Japanese readings for
each Chinese word. Those readings are going to be used to evaluate the look-up
coverage and average rank of Pinyomi system. 

As some Chinese hanzi is not readable to Japanese. In this experiment, the
simulus(word) should be words which consist of readable hanzis.

1. produce a readable hanzi list for Japanese;
2. produce a readable word list from Chinese vocabulary in Ch-Jp dictionary. 
3. randomly select a sample of sitmulus with size NUM_STIMULUS_PER_USER to do
experiment.  The size here should be decided by theory of sampling survey. 
4. collect response(readings) of stimulus(word) from user.
5. analyze the experiment data. 


Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.