14.Dec.10th
Done
report draft 2
To do
final report; debug reverse maximun matching
13.Dec.3rd
Done
report draft 1
To do
report draft 2, segmentation patch 4
12.Nov.26th
Done
Partial QA implementation
Todo
report draft 1
11.Nov.19th
Done:
Second part of question answering system
TO DO:
QA partial implementation
10.Nov.12th
Done:
Starting Question and Answering Part
To Do
Find algorithm for extracting the answers from candidate pages.
09.Nov.5th
Have done:
Postagging
TO DO:
Question and anserwing
Deliverable 3
08.Oct.29nd
Was Done:
word segmentation finalize
pos tagging start
To do:
Pos tagging program first draft version.
07.Oct.22nd
Finalize Chinese Segmentation.
Revise some structure of the code.
TODO
POS slides
06.Oct.15th
continue on chinese segmentation
05.Oct.1st
Done:
Explaining CRF;
Explaining CWS;
To Do:
Trying to implement CRF in two weeks;
04.Sept.24th
Done this week:
Deliverable 1
To Do:
CRF and Chinese segmentation
03.Sept.17th
Things talked today
Some bugs metioned:
Searching Chinese words in English Setting results in Chinese Page with English Lang: lang=zh
All Chinese Pages are unsafe: safe:all
In windows, Chinese text are saved(?) into unicode (not sure if this is a bug but can figure out later)
TODO:
Use Google Trends to calculate score for words
02.Sept.10th
Stuff talked about today:
Chinese suggestion word list and the format
How to generated the list using 4 gram / 5 gram
Stuff Todo:
Fix the current Chinese tokenizer bug in yioop
Generate the 4 gram / 5 gram file
01.Sept.3rd
Fixed some proposal issues.
Talked about the project/subject I need to work on.
Talked about the localization in Yioop.