0

I did go through the documentation available linked below. But things are still not clear as in how I should proceed? I followed the correct input training format but gets error as follows.

cmd command:

./opennlp ChunkerTrainerME -model hn-chunker.bin -lang hn -data sampletrain.txt -encoding UTF-8

Error:

Skipping corrupt line: इसके PRP NP
Skipping corrupt line: साथ  NST NP
Skipping corrupt line: ही   RP  NP
Skipping corrupt line: पार्टी   NN  NP2
Skipping corrupt line: ने   PSP NP2
Skipping corrupt line: सरकार    NN  NP3
Skipping corrupt line: से   PSP NP3
Skipping corrupt line: इस   DEM NP4
Skipping corrupt line: मसले NN  NP4
Skipping corrupt line: पर   PSP NP4
Skipping corrupt line: बयान NN  NP5
Skipping corrupt line: देने VM  VGNN
Skipping corrupt line: की   PSP VGNN
Skipping corrupt line: मांग NN  NP6
Skipping corrupt line: की   VM  VGF
Skipping corrupt line: है   VAUX    VGF

done. 0 events
Indexing...  done.
Sorting and merging events... Done indexing.
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.chunker.ChunkerME.train(ChunkerME.java:214)
at opennlp.tools.cmdline.chunker.ChunkerTrainerTool.run(ChunkerTrainerTool.java:68)
at opennlp.tools.cmdline.CLI.main(CLI.java:222)

Reference: http://opennlp.apache.org/documentation/1.5.3/manual/opennlp.html#tools.chunker

Linguist
  • 123
  • 1
  • 10

1 Answers1

0

I'm not sure if you are still looking for an answer, but I found out the issue was in your training text file it requires only on space between the words and tags. You may have multiple spaces between tags.

For example: Skipping corrupt line: पार्टी NN NP2

  1. There are 3 spaces between पार्टी and NN.
  2. There are 3 spaces between NN and NP2.
jocey
  • 252
  • 4
  • 14