|
--- |
|
language: |
|
- as |
|
- bn |
|
- gu |
|
- hi |
|
- kn |
|
- ml |
|
- mr |
|
- or |
|
- pa |
|
- ta |
|
- te |
|
license: mit |
|
datasets: |
|
- Samanantar |
|
tags: |
|
- ner |
|
- Pytorch |
|
- transformer |
|
- multilingual |
|
- nlp |
|
- indicnlp |
|
--- |
|
|
|
# IndicNER |
|
IndicNER is a model trained to complete the task of identifying named entities from sentences in Indian languages. Our model is specifically fine-tuned to the 11 Indian languages mentioned above over millions of sentences. The model is then benchmarked over a human annotated testset and multiple other publicly available Indian NER datasets. |
|
The 11 languages covered by IndicBERT are: Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil, Telugu. |
|
The link to our GitHub repository containing all our code can be found [here](https://github.com/AI4Bharat/indicner). The link to our paper can be found here. |
|
|
|
## Training Corpus |
|
Our model was trained on a [dataset](https://huggingface.co/datasets/ai4bharat/naamapadam) which we mined from the existing [Samanantar Corpus](https://huggingface.co/datasets/ai4bharat/samanantar). We used a bert-base-multilingual-uncased model as the starting point and then fine-tuned it to the NER dataset mentioned previously. |
|
|
|
## Evaluation Results |
|
Benchmarking on our testset. |
|
|
|
Language | bn | hi | kn | ml | mr | gu | ta | te | as | or | pa |
|
-----| ----- | ----- | ------ | -----| ----- | ----- | ------ | -----| ----- | ----- | ------ |
|
F1 score | 79.75 | 82.33 | 80.01 | 80.73 | 80.51 | 73.82 | 80.98 | 80.88 | 62.50 | 27.05 | 74.88 |
|
|
|
The first 5 languages (bn, hi, kn, ml, mr ) have large human annotated testsets consisting of around 500-1000 sentences. The next 3 (gu, ta, te) have smaller human annotated testsets with only around 50 sentences. The final 3 (as, or, pa) languages have mined projected testsets not supervised by humans. |
|
|
|
|
|
## Downloads |
|
Download from this same Huggingface repo. |
|
|
|
|
|
|
|
|
|
|
|
<!-- citing information --> |
|
## Citing |
|
|
|
If you are using IndicNER, please cite the following article: |
|
``` |
|
@misc{mhaske2022indicner, |
|
title={Naamapadam: A Large-Scale Named Entity Annotated Data for Indic |
|
Languages}, |
|
author={Arnav Mhaske, Harshit Kedia, Rudramurthy. V, Anoop Kunchukuttan, Pratyush Kumar, Mitesh Khapra}, |
|
year={2022}, |
|
eprint={to be published soon}, |
|
} |
|
``` |
|
We would like to hear from you if: |
|
|
|
- You are using our resources. Please let us know how you are putting these resources to use. |
|
- You have any feedback on these resources. |
|
|
|
|
|
<!-- License --> |
|
## License |
|
|
|
The IndicNER code (and models) are released under the MIT License. |
|
|
|
|
|
|
|
<!-- Contributors --> |
|
## Contributors |
|
- Arnav Mhaske <sub> ([AI4Bharat](https://ai4bharat.org), [IITM](https://www.iitm.ac.in)) </sub> |
|
- Harshit Kedia <sub> ([AI4Bharat](https://ai4bharat.org), [IITM](https://www.iitm.ac.in)) </sub> |
|
- Anoop Kunchukuttan <sub> ([AI4Bharat](https://ai4bharat.org), [Microsoft](https://www.microsoft.com/en-in/)) </sub> |
|
- Rudra Murthy <sub> ([AI4Bharat](https://ai4bharat.org), [IBM](https://www.ibm.com))</sub> |
|
- Pratyush Kumar <sub> ([AI4Bharat](https://ai4bharat.org), [Microsoft](https://www.microsoft.com/en-in/), [IITM](https://www.iitm.ac.in)) </sub> |
|
- Mitesh M. Khapra <sub> ([AI4Bharat](https://ai4bharat.org), [IITM](https://www.iitm.ac.in)) </sub> |
|
|
|
This work is the outcome of a volunteer effort as part of [AI4Bharat initiative](https://ai4bharat.org). |
|
|
|
|
|
<!-- Contact --> |
|
## Contact |
|
- Anoop Kunchukuttan ([anoop.kunchukuttan@gmail.com](mailto:anoop.kunchukuttan@gmail.com)) |
|
- Mitesh Khapra ([miteshk@cse.iitm.ac.in](mailto:miteshk@cse.iitm.ac.in)) |
|
- Pratyush Kumar ([pratyush@cse.iitm.ac.in](mailto:pratyush@cse.iitm.ac.in)) |
