https://github.com/pierremtb/paragraph-vector-baselines

Course project at McGill University. Reproducing baselines of a state-of-the-art paper in Natural Language Processing.
https://github.com/pierremtb/paragraph-vector-baselines

data-science mcgill-university natural-language-processing python3

Last synced: over 1 year ago
JSON representation

Course project at McGill University. Reproducing baselines of a state-of-the-art paper in Natural Language Processing.

• Host: GitHub
• URL: https://github.com/pierremtb/paragraph-vector-baselines
• Owner: pierremtb
• License: mit
• Created: 2019-05-15T10:43:02.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2019-05-15T10:53:11.000Z (about 7 years ago)
• Last Synced: 2025-02-11T23:56:29.253Z (over 1 year ago)
• Topics: data-science, mcgill-university, natural-language-processing, python3
• Language: Python
• Size: 10.9 MB
• Stars: 0
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

          
# COMP 551 Mini Project 4

2019-04-17

Segev, Michael

Jacquier, Pierre

Han, Zhenze

Models and experiments are split in seperate python scripts that 

all use common classes to load files and save models to file.

1. NaiveBayesBench.py

	Run this file to test different feature extraction pipelines 

	with a NB classifier on Stanford Sentiment Treebank.

2. SVMBench.py

	Run this file to train and test/validate Support Vector Machine 

	model on Stanford Sentiment Treebank.

3. RNNBench.py

	Run this file to train and test/validate Recursive Neural 

	Network model on Stanford Sentiment Treebank.

4. DecisionTreesBench.py

	Run this file to train and test/validate extremely random trees 

	model on Stanford Sentiment Treebank.

5. metaClassifier.py

	Run this file to train and test/validate stacking ensemble 

	meta-classifier on on Stanford Sentiment Treebank using 

	pre-trained models saved as pickle files.

	

## Original Paper

```

@inproceedings{le2014distributed,

	title={Distributed representations of sentences and documents},

	author={Le, Quoc and Mikolov, Tomas},

	booktitle={International conference on machine learning},

	pages={1188--1196},

	year={2014}

}

```

## Library Dependecies:

	re

	numpy

	scikit-learn

	keras

	tensorflow-gpu

## Copyright

[MIT license](LICENSE.md)