Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/zabir-nabil/bangla-news-rnn
Bangla news classification and generation
https://github.com/zabir-nabil/bangla-news-rnn
bangla-dataset bangla-news-rnn bangla-nlp bilstm dataset news text-classification
Last synced: about 1 month ago
JSON representation
Bangla news classification and generation
- Host: GitHub
- URL: https://github.com/zabir-nabil/bangla-news-rnn
- Owner: zabir-nabil
- License: mit
- Created: 2019-07-09T14:20:21.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2020-10-21T06:32:07.000Z (over 3 years ago)
- Last Synced: 2024-02-18T13:32:09.229Z (4 months ago)
- Topics: bangla-dataset, bangla-news-rnn, bangla-nlp, bilstm, dataset, news, text-classification
- Language: Jupyter Notebook
- Homepage:
- Size: 130 KB
- Stars: 19
- Watchers: 1
- Forks: 11
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Lists
- awesome-bangla - Bangla News Category Classification with Bidirectional LSTM
README
# bangla-news-rnn
### Bangla Newspaper Dataset
400k+ bangla news samples, 25+ categories https://www.kaggle.com/furcifer/bangla-newspaper-dataset
v2 dataset: https://www.kaggle.com/furcifer/bangla-newspaper-dataset?select=data_v2
DOI: 10.34740/kaggle/dsv/1576225
### Source
Data collected from https://www.prothomalo.com/archive [**Copyright owned by the actual source**]
### Inspiration
The dataset can be used for bangla text classification and generation experiments.
### Todo
- [x] Starter Bidirectional LSTM (91% test accuracy)
- [x] Weight file [tf-gpu weights](https://drive.google.com/drive/folders/1KP5E6K2xTTfLW_5JAM_H1kjyYv_uphAt) (Trained with RTX-2080 Ti, tensorflow-gpu, keras)
- [ ] BERT
- [ ] XLNet
- [ ] Starter Generative Model