inltk
Code-Mixed Languages support
iNLTK aims to provide out of the box support for various NLP tasks that an application developer might need for Indic languages. Paper for iNLTK library has been accepted at EMNLP-2020's NLP-OSS workshop. Here's the link to the paper
Checkout detailed docs along with Installation instructions at https://inltk.readthedocs.io
| Language | Code |
|---|---|
| Hindi | hi |
| Punjabi | pa |
| Gujarati | gu |
| Kannada | kn |
| Malayalam | ml |
| Oriya | or |
| Marathi | mr |
| Bengali | bn |
| Tamil | ta |
| Urdu | ur |
| Nepali | ne |
| Sanskrit | sa |
| English | en |
| Telugu | te |
| Language | Script | Code |
|---|---|---|
| Hinglish (Hindi+English) | Latin | hi-en |
| Tanglish (Tamil+English) | Latin | ta-en |
| Manglish (Malayalam+English) | Latin | ml-en |
| Language | Repository | Dataset used for Language modeling | Perplexity of ULMFiT LM (on validation set) |
Perplexity of TransformerXL LM (on validation set) |
Dataset used for Classification | Classification: Test set Accuracy |
Classification: Test set MCC |
Classification: Notebook for Reproducibility |
ULMFiT Embeddings visualization | TransformerXL Embeddings visualization |
|---|---|---|---|---|---|---|---|---|---|---|
| Hindi | NLP for Hindi | Hindi Wikipedia Articles - 172k Hindi Wikipedia Articles - 55k |
34.06 35.87 |
26.09 34.78 |
BBC News Articles IIT Patna Movie Reviews IIT Patna Product Reviews |
78.75 57.74 75.71 |
0.71 0.37 0.59 |
Notebook Notebook Notebook |
Hindi Embeddings projection | Hindi Embeddings projection |
| Bengali | NLP for Bengali | Bengali Wikipedia Articles | 41.2 | 39.3 | Bengali News Articles (Soham Articles) | 90.71 | 0.87 | Notebook | Bengali Embeddings projection | Bengali Embeddings projection |
| Gujarati | NLP for Gujarati | Gujarati Wikipedia Articles | 34.12 | 28.12 | iNLTK Headlines Corpus - Gujarati | 91.05 | 0.86 | Notebook | Gujarati Embeddings projection | Gujarati Embeddings projection |
| Malayalam | NLP for Malayalam | Malayalam Wikipedia Articles | 26.39 | 25.79 | iNLTK Headlines Corpus - Malayalam | 95.56 | 0.93 | Notebook | Malayalam Embeddings projection | Malayalam Embeddings projection |
| Marathi | NLP for Marathi | Marathi Wikipedia Articles | 18 | 17.42 | iNLTK Headlines Corpus - Marathi | 92.40 | 0.85 | Notebook | Marathi Embeddings projection | Marathi Embeddings projection |
| Tamil | NLP for Tamil | Tamil Wikipedia Articles | 19.80 | 17.22 | iNLTK Headlines Corpus - Tamil | 95.22 | 0.92 | Notebook | Tamil Embeddings projection | Tamil Embeddings projection |
| Punjabi | NLP for Punjabi | Punjabi Wikipedia Articles | 24.40 | 14.03 | IndicNLP News Article Classification Dataset - Punjabi | 97.12 | 0.96 | Notebook | Punjabi Embeddings projection | Punjabi Embeddings projection |
| Kannada | NLP for Kannada | Kannada Wikipedia Articles | 70.10 | 61.97 | IndicNLP News Article Classification Dataset - Kannada | 98.87 | 0.98 | Notebook | Kannada Embeddings projection | Kannada Embeddings projection |
| Oriya | NLP for Oriya | Oriya Wikipedia Articles | 26.57 | 26.81 | IndicNLP News Article Classification Dataset - Oriya | 98.83 | 0.98 | Notebook | Oriya Embeddings Projection | Oriya Embeddings Projection |
| Sanskrit | NLP for Sanskrit | Sanskrit Wikipedia Articles | ~6 | ~3 | Sanskrit Shlokas Dataset | 84.3 (valid set) | Sanskrit Embeddings projection | Sanskrit Embeddings projection | ||
| Nepali | NLP for Nepali | Nepali Wikipedia Articles | 31.5 | 29.3 | Nepali News Dataset | 98.5 (valid set) | Nepali Embeddings projection | Nepali Embeddings projection | ||
| Urdu | NLP for Urdu | Urdu Wikipedia Articles | 13.19 | 12.55 | Urdu News Dataset | 95.28 (valid set) | Urdu Embeddings projection | Urdu Embeddings projection | ||
| Telugu | NLP for Telugu | Telugu Wikipedia Articles | 27.47 | 29.44 | Telugu News Dataset Telugu News Andhra Jyoti |
95.4 92.09 |
Notebook Notebook |
Telugu Embeddings projection | Telugu Embeddings projection | |
| Tanglish | NLP for Tanglish | Synthetic Tanglish Dataset | 37.50 | - | Dravidian Codemix HASOC @ FIRE 2020 Dravidian Codemix Sentiment Analysis @ FIRE 2020 |
F1 Score: 0.88 F1 Score: 0.62 |
- | Notebook Notebook |
Tanglish Embeddings Projection | - |
| Manglish | NLP for Manglish | Synthetic Manglish Dataset | 45.84 | - | Dravidian Codemix HASOC @ FIRE 2020 Dravidian Codemix Sentiment Analysis @ FIRE 2020 |
F1 Score: 0.74 F1 Score: 0.69 |
- | Notebook Notebook |
Manglish Embeddings Projection | - |
| Hinglish | NLP for Hinglish | Synthetic Hinglish Dataset | 86.48 | - | - | - | - | - | Hinglish Embeddings Projection | - |
Note: English model has been directly taken from fast.ai
| Language | Repository | Dataset used for Classification | Results on using complete training set |
Percentage Decrease in Training set size |
Results on using reduced training set without Paraphrases |
Results on using reduced training set with Paraphrases |
|---|---|---|---|---|---|---|
| Hindi | NLP for Hindi | IIT Patna Movie Reviews | Accuracy: 57.74 MCC: 37.23 |
80% (2480 -> 496) | Accuracy: 47.74 MCC: 20.50 |
Accuracy: 56.13 MCC: 34.39 |
| Bengali | NLP for Bengali | Bengali News Articles (Soham Articles) | Accuracy: 90.71 MCC: 87.92 |
99% (11284 -> 112) | Accuracy: 69.88 MCC: 61.56 |
Accuracy: 74.06 MCC: 65.08 |
| Gujarati | NLP for Gujarati | iNLTK Headlines Corpus - Gujarati | Accuracy: 91.05 MCC: 86.09 |
90% (5269 -> 526) | Accuracy: 80.88 MCC: 70.18 |
Accuracy: 81.03 MCC: 70.44 |
| Malayalam | NLP for Malayalam | iNLTK Headlines Corpus - Malayalam | Accuracy: 95.56 MCC: 93.29 |
90% (5036 -> 503) | Accuracy: 82.38 MCC: 73.47 |
Accuracy: 84.29 MCC: 76.36 |
| Marathi | NLP for Marathi | iNLTK Headlines Corpus - Marathi | Accuracy: 92.40 MCC: 85.23 |
95% (9672 -> 483) | Accuracy: 84.13 MCC: 68.59 |
Accuracy: 84.55 MCC: 69.11 |
| Tamil | NLP for Tamil | iNLTK Headlines Corpus - Tamil | Accuracy: 95.22 MCC: 92.70 |
95% (5346 -> 267) | Accuracy: 86.25 MCC: 79.42 |
Accuracy: 89.84 MCC: 84.63 |
For more details around implementation or to reproduce results, checkout respective repositories.
If you would like to add support for language of your own choice to iNLTK, please start with checking/raising a issue here
Please checkout the steps I'd mentioned here for Telugu to begin with. They should be almost similar for other languages as well.
If you would like to take iNLTK's models and refine them with your own dataset or build your own custom models on top of it, please check out the repositories in the above table for the language of your choice. The repositories above contain links to datasets, pretrained models, classifiers and all of the code for that.
If you wish for a particular functionality in iNLTK - Start by checking/raising a issue here
Shout out if you want to help :)
Shout out if you want to lead :)
If you use this library in your research, please consider citing:
@inproceedings{arora-2020-inltk,
title = "i{NLTK}: Natural Language Toolkit for Indic Languages",
author = "Arora, Gaurav",
booktitle = "Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.nlposs-1.10",
doi = "10.18653/v1/2020.nlposs-1.10",
pages = "66--71",
abstract = "We present iNLTK, an open-source NLP library consisting of pre-trained language models and out-of-the-box support for Data Augmentation, Textual Similarity, Sentence Embeddings, Word Embeddings, Tokenization and Text Generation in 13 Indic Languages. By using pre-trained models from iNLTK for text classification on publicly available datasets, we significantly outperform previously reported results. On these datasets, we also show that by using pre-trained models and data augmentation from iNLTK, we can achieve more than 95{%} of the previous best performance by using less than 10{%} of the training data. iNLTK is already being widely used by the community and has 40,000+ downloads, 600+ stars and 100+ forks on GitHub. The library is available at https://github.com/goru001/inltk.",
}
