DigitalUmuganda/Joeynmt-kin-en

Kinyarwanda-to-English Machine Translation

This model is a Kinyarwanda-to-English machine translation model, it was built and trained using JoeyNMT framework. The translation model uses transformer encoder-decoder based architecture. It was trained on a 47,211-long English-Kinyarwanda bitext dataset prepared by Digital Umuganda.

Model architecture

Encoder && Decoder

Type: Transformer

Numlayer: 6 Numheads: 8 Embeddingdim: 256 ffsize: 1024 Dropout: 0.1 Layer_norm: post Initializer: xavier Total params: 12563968

Pre-processing

Tokenizertype: subword-nmt nummerges: 4000 BPE encoding learned on the bitext, separate vocabularies for each language Pretokenizer: None No lowercase applied

Training

Optimizer: Adam Loss: crossentropy Epochs: 30 Batch_size: 256 Number of GPUs: 1

Evaluation

Evaluationmetrics: Bluescore, chrf Tokenization: None Beamwidth: 15 Beamalpha: 1.0

Tools

• —joeyNMT 2.0.0
• —datasets
• —pandas
• —numpy
• —transformers
• —sentencepiece
• —pytorch(with cuda)
• —sacrebleu
• —protobuf>=3.20.1

How to train

Use the following link for more information

Translation

To install joeyNMT run:

$ git clone https://github.com/joeynmt/joeynmt.git
$ cd joeynmt
$ pip install . -e

Interactive translation(stdin):

$ python -m joeynmt translate args.yaml

File translation:

$ python -m joeynmt translate args.yaml < src_lang.txt > hypothesis_trg_lang.txt

Accuracy measurement

Sacrebleu installation:

$ pip install sacrebleu

Measurement(bleu_score, chrf):

$ sacrebleu reference.tsv -i hypothesis.tsv -m bleu chrf 

To-do

Test the model using different datasets including the jw300 Use the Digital Umuganda dataset on some available State Of The Art(SOTA) models. * Expand the dataset

Result

The following result was obtained using sacrebleu.

Kinyarwanda-to-English:

Blue: 79.87
Chrf: 84.40