|
--- |
|
license: cc-by-4.0 |
|
language: |
|
- hi |
|
- en |
|
tags: |
|
- hi |
|
- en |
|
- codemix |
|
datasets: |
|
- L3Cube-HingCorpus |
|
--- |
|
|
|
## HingGPT |
|
HingGPT is a Hindi-English code-mixed GPT model trained on roman text. It is a GPT2 model trained on L3Cube-HingCorpus. |
|
<br> |
|
[dataset link] (https://github.com/l3cube-pune/code-mixed-nlp) |
|
|
|
More details on the dataset, models, and baseline results can be found in our [paper] (https://arxiv.org/abs/2204.08398) |
|
|
|
``` |
|
@InProceedings{nayak-joshi:2022:WILDRE6, |
|
author = {Nayak, Ravindra and Joshi, Raviraj}, |
|
title = {L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models}, |
|
booktitle = {Proceedings of The WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference}, |
|
month = {June}, |
|
year = {2022}, |
|
address = {Marseille, France}, |
|
publisher = {European Language Resources Association}, |
|
pages = {7--12} |
|
} |
|
``` |