Re: Not Able to Extract Person Entities by Creating Custom Model

[Jörn Kottmann]

Hello, please don't double post. The training format requires that there are spaces between words and the annotation tags. You are missing the spaces, as far as I can see. You have:  ?<START:person> Kunal ###<END>### . but it should be (added spaces):  ? <START:person> Kunal ### <END> ### . Anyway if you need to annotate a bigger amount of data I strongly suggest to use an annotation tool. HTH, Jörn On 12/16/2013 08:33 AM, kunal.kishore.si...@accenture.com wrote: Dear OPENNLP Experts   I am trying to build the Person Statistical model using OPEN NLP API’s , refer to java class “OpenNLPPersonTrainer” .   Training data is as in “train.txt”   However , I am getting the following message.   Indexing events using cutoff of 5          Computing event counts...  java.io.IOException: Found unexpected annotation: ?<START:person> Kunal ###<END>### . Incorporating indexed data for training...  Exception in thread "main" java.lang.NullPointerException        at opennlp.maxent.GISTrainer.trainModel(GISTrainer.java:263)        at opennlp.maxent.GIS.trainModel(GIS.java:256)        at opennlp.model.TrainUtil.train(TrainUtil.java:184)        at opennlp.tools.namefind.NameFinderME.train(NameFinderME.java:366)        at opennlp.tools.namefind.NameFinderME.train(NameFinderME.java:432)        at opennlp.tools.namefind.NameFinderME.train(NameFinderME.java:443)        at opennlp.tools.namefind.NameFinderME.train(NameFinderME.java:448)        at com.test.OpenNLPPersonTrainer.main(OpenNLPPersonTrainer.java:73)   I have tried out almost everything but not able to move  forward, please let me know, what I am doing wrong.           Thanks & Regards,   Kunal Kishore Sinha Information Management Capability, India Delivery Center, Bangalore-7|Desk: +91 8067051455 Mobile No:9035749331 mailto:kunal.kishore.si...@accenture.com     This message is for the designated recipient only and may contain privileged, proprietary, or otherwise confidential information. If you have received it in error, please notify the sender immediately and delete the original. Any other use of the e-mail by you is prohibited. Where allowed by local law, electronic communications with Accenture and its affiliates, including e-mail and instant messaging (including content), may be scanned by our systems for the purposes of information security and assessment of internal compliance with Accenture policy. . ______________________________________________________________________________________ www.accenture.com