Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/jegp/langprocexam
Exam for language processing II
https://github.com/jegp/langprocexam
Last synced: 11 days ago
JSON representation
Exam for language processing II
- Host: GitHub
- URL: https://github.com/jegp/langprocexam
- Owner: Jegp
- Created: 2017-06-15T15:37:49.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2017-06-16T16:10:45.000Z (over 7 years ago)
- Last Synced: 2024-10-28T12:59:13.052Z (about 2 months ago)
- Language: TeX
- Size: 45 MB
- Stars: 0
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Language processing II exam
An exam for a course on language processing
## Requirements
To reproduce the results you need to install python3 and the following
pip3 packages (I highly recommend using a virtualenv):* Numpy
* Sklearn
* Tensorflow
* Keras## Repository structure
The preprocessing is done in the ``preprocessing.py`` file, and the results
(included) can be found in the ``data.npz`` file. The proprocessor uses the
data from the ``scaledata`` folder.Four models are constructed using the proprocessed data: a linear model,
a linear model with a tf-idf score, a recurrent neural network with LSTMs and
a LSTM with tf-idf. They are located in the correspondingly named python files.
Simply running those files with ``python3`` should run the models, given
the prerequisites have been correctly installed.## Contact
[email protected]