[SOLVED] Extracting names

laflaca

Hello everyone,

I am working on my master thesis and I am new to Rapid Miner. What I need to do is extract names from text (mostly short comments of 3, 4 sentences). These comments are in excel sheets and are in English, German and Spanish. Some of the names are not in capital letters. I really have trouble figuring this out

Thx for any suggestions in advance!

StaryVena

Hello,
try download some where list of all names (parse some phone book) and use it as dictionary. Or if they have some special position in text, you can use regular expression to parse it.

Best,
Václav

RWingerter

For a start, try "Filter Tokens (by POS Tags)". It's under Text Processing > Filtering.

Roland

RWingerter

See example in this message:

http://rapid-i.com/rapidforum/index.php/topic,4916.msg22426.html

Roland

laflaca

Thx a lot!