https://github.com/linmx0130/parserChiang

Naïve transition-based dependency parser in Gluon
https://github.com/linmx0130/parserChiang

conll-u dependency-parser gluon mxnet parser

Last synced: 2 days ago
JSON representation

Naïve transition-based dependency parser in Gluon

• Host: GitHub
• URL: https://github.com/linmx0130/parserChiang
• Owner: linmx0130
• License: mit
• Created: 2017-11-29T06:53:40.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2019-10-17T07:52:21.000Z (over 5 years ago)
• Last Synced: 2024-11-08T18:46:09.657Z (5 months ago)
• Topics: conll-u, dependency-parser, gluon, mxnet, parser
• Language: Python
• Homepage:
• Size: 56.6 KB
• Stars: 6
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-MXNet - parserChiang(Gluon:star:)

README

        
parserChiang - Naïve Transition-based Dependency Parser in Gluon

=====

This repo support CoNLL format, which is adapted by [Universal Dependencies](http://universaldependencies.org/) Project. parserChiang is implemented with great [MXNet gluon](http://gluon.mxnet.io/).

![Babel Towel: right bottom part](https://upload.wikimedia.org/wikipedia/commons/thumb/9/9e/Pieter_Bruegel_the_Elder_-_The_Tower_of_Babel_%28Vienna%29_-_Google_Art_Project-x2-y1.jpg/600px-Pieter_Bruegel_the_Elder_-_The_Tower_of_Babel_%28Vienna%29_-_Google_Art_Project-x2-y1.jpg)

### 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 \, read LICENSE for more details.