On 24/02/12 05:09, James Kosin wrote:
Jim,
Maybe the problem is how you have created the dictionary. The
DictionaryNameFinder's find() method is a greedy method that will match
as many tokens as possible.
If it isn't matching more than one token than that is probably all the
dictionary contains per entry.
Look at the simple example in the test packages for
opennlp.tools.namefind DictionaryNameFinderTest.java in the source packages.
There has a good example.
James
Hi James,
Well, the dictionary i created manually...basically i extracted all the
drug-names from drugbank.xml and wrote them to a txt file (one entry per
line). then i processed that text-file in order to produce the xml
version of the proper dictionary. What i have after doing all that is a
file with contents of the type:
<?xml version="1.0" encoding="UTF-8"?>
<dictionary case_sensitive="false">
<entry><token>Lepirudin</token></entry>
<entry><token>Cetuximab</token></entry>
<entry><token>Dornase Alfa</token></entry>
<entry><token>Denileukin diftitox</token></entry>
<entry><token>Etanercept</token></entry>
<entry><token>Bivalirudin</token></entry>
<entry><token>Leuprolide</token></entry>
<entry><token>Peginterferon alfa-2a</token></entry>
<entry><token>Alteplase</token></entry>
......
......
......etc etc
As you can see some drugs are multi-word entities and also the first
character of each word is capitalized. Whenever i call the find() method
all i'm getting are the exact matches which means that case-sensitivity
doesn ot work either!!! For example i'm getting "Cetuximab" but not
"cetuximab"...so the problem is twofold...Firstly and more importantly I
cannot find multi-word entities even though they do exist in the
dictionary and the test data. Secondly, even though i'm setting
case_sensitive="false" in both the xml file and the constructor of the
DictionaryNameFinder, the actual results that i 'm getting are always
case-sensitive!!!
Can you see any problems with the xml file?
Jim
