---
language: sw
datasets:
- kenyacorpus_v2
license: cc-by-4.0
model-index:
- name: innocent-charles/Swahili-question-answer-latest-cased
  results:
  - task:
      type: question-answering
      name: Question Answering
    dataset:
      name: kenyacorpus
      type: kenyacorpus
      config: kenyacorpus
      split: validation
    metrics:
    - name: Exact Match
      type: exact_match
      value: 51.9309
      verified: true
    - name: F1
      type: f1
      value: 63.9501
      verified: true
    - name: total
      type: total
      value: 445
      verified: true
---

# SWAHILI QUESTION - ANSWER MODEL

This is the [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) model, fine-tuned using the [KenyaCorpus](https://github.com/Neurotech-HQ/Swahili-QA-dataset) dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Question Answering in Swahili Language.

Question answering (QA) is a computer science discipline within the fields of information retrieval and NLP that help in the development of systems in such a way that, given a question in natural language, can extract relevant information from provided data and present it in the form of natural language answers.


## Overview
**Language model used:** bert-base-multilingual-cased  
**Language:** Kiswahili 
**Downstream-task:** Extractive Swahili QA  
**Training data:** KenyaCorpus 
**Eval data:** KenyaCorpus 
**Code:**  See [an example QA pipeline on Haystack](https://blog.neurotech.africa/building-swahili-question-and-answering-with-haystack/)  
**Infrastructure**: AWS NVIDIA A100 Tensor Core GPU 

## Hyperparameters

```
batch_size = 16
n_epochs = 10
base_LM_model = "bert-base-multilingual-cased"
max_seq_len = 386
learning_rate = 3e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64
``` 

## Usage

### In Haystack
Haystack is an NLP framework by deepset. You can use this model in a Haystack pipeline to do question answering at scale (over many documents). To load the model in [Haystack](https://github.com/deepset-ai/haystack/):
```python
reader = FARMReader(model_name_or_path="innocent-charles/Swahili-question-answer-latest-cased")
# or 
reader = TransformersReader(model_name_or_path="innocent-charles/Swahili-question-answer-latest-cased",tokenizer="innocent-charles/Swahili-question-answer-latest-cased")
```
For a complete example of ``Swahili-question-answer-latest-cased`` being used for Swahili Question Answering, check out the [Tutorials in Haystack Documentation](https://haystack.deepset.ai)

### In Transformers
```python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "innocent-charles/Swahili-question-answer-latest-cased"

# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
    'question': 'Asubuhi ilitupata pambajioi pa hospitali gani?',
    'context': 'Asubuhi hiyo ilitupata pambajioni pa hospitali ya Uguzwa.'
}
res = nlp(QA_input)

# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
```

## Performance

```
"exact": 51.87029394424324,
"f1": 63.91251169582613,

"total": 445,
"HasAns_exact": 50.93522267206478,
"HasAns_f1": 62.02838248389763,
"HasAns_total": 386,
"NoAns_exact": 49.79983179142137,
"NoAns_f1": 60.79983179142137,
"NoAns_total": 59
```


## Special consideration

The project is still going, hence the model is still updated after training the model in more data, Therefore pull requests are welcome to contribute to increase the performance of the model. 

## Author
**Innocent Charles:** contact@innocentcharles.com  

## About Me

<P>
I build good things using Artificial Intelligence ,Data and Analytics , with over 3 Years of Experience as Applied AI Engineer & Data scientist from a strong background in Software Engineering ,with passion and extensive experience in Data and Businesses.
</P>


[Linkedin](https://www.linkedin.com/in/innocent-charles/) | [GitHub](https://github.com/innocent-charles) | [Website](innocentcharles.com)