Skip to content

linmx0130/parserChiang

Repository files navigation

parserChiang - Naïve Transition-based Dependency Parser in Gluon

This repo support CoNLL format, which is adapted by Universal Dependencies Project. parserChiang is implemented with great MXNet gluon.

Babel Towel: right bottom part

Models

There are different models in this repo:

  1. [DEPRECATED] default/: The default parser model using only word features. It is the baseline of all other models.
  2. [DEPRECATED] pos_aid/: This parser model requires standard POS tagging during inference, which is provided in CoNLL dataset. In practice, you may use Stanford NLP tools to get good POS tags.
  3. [DEPRECATED] pos_joint/: This parser model will predict POS tags.
  4. pos_deprel_joint/: This parser model will predict POS tags and dependent relation label. LAS index requires the output from this model.
  5. [DEPRECATED] pos_aid_deprel_joint/: This parser model requires standard POS tagging during inference, and will predict ependent relation label.

The models marked with [DEPRECATED] will not be updated to latest functions.

Usage

Data should be put into data/ directory. Train the model with

$ python3 train_pos_parser.py

If the training procedure runs on GPU and the loss value become NaN abruptly, change to CPU training with following command:

$ python3 train_pos_parser.py --cpu

The maintainer is still working on this bug.

Then it will create a directory named model_dumps_{Date}_{Time} to store the model dump. Test it with

$ python3 test_pos_parser.py [model_path] [model_file]

Notes

This implementation is a low-performance transition-based parser in both training speed and predicition accuracy. I created it as a toy model simply for learning natural language processing. DO NOT USE IT IN ANY REAL WORLD TASKS.

Have fun with it!

License

Copyright 2017-2019 Mengxiao Lin <[email protected]>, read LICENSE for more details.

About

Naïve transition-based dependency parser in Gluon

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages