---
license: apache-2.0
datasets:
- projecte-aina/CA-ZH_Parallel_Corpus
language:
- zh
- ca
base_model:
- facebook/m2m100_1.2B
---
## Projecte Aina’s Catalan-Chinese machine translation model

## Table of Contents
<details>
<summary>Click to expand</summary>

- [Model description](#model-description)
- [Intended uses and limitations](#intended-uses-and-limitations)
- [How to use](#how-to-use)
- [Limitations and bias](#limitations-and-bias)
- [Training](#training)
- [Evaluation](#evaluation)
- [Additional information](#additional-information)

</details>

 
## Model description

This machine translation model is built upon the M2M100 1.2B, fine-tuned specifically for Catalan-Chinese translation. 
It is trained on a combination of Catalan-Chinese datasets 
totalling 94,187,858 sentence pairs. 113,305 sentence pairs were parallel data collected from the web, while the remaining 94,074,553 sentence pairs 
were parallel synthetic data created using the 
[Aina Project's Spanish-Catalan machine translation model](https://huggingface.co/projecte-aina/aina-translator-es-ca) and the [Aina Project's English-Catalan machine translation model](https://huggingface.co/projecte-aina/aina-translator-en-ca). 

Following the fine-tuning phase, Contrastive Preference Optimization (CPO) was applied to further refine the model's outputs. CPO training involved pairs of "chosen" and "rejected" translations for a total of 4,006 sentences. These sentences were sourced from the Flores development set (997 sentences), the Flores devtest set (1,012 sentences), and the NTREX set (1,997 sentences).

The model was evaluated on the Projecte Aina's Catalan-Chinese evaluation dataset, which contains 1022 sentences. 

## Intended uses and limitations

You can use this model for machine translation from Catalan to simplified Chinese.

## How to use

### Usage

Translate a sentence using python
```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model_id = "projecte-aina/aina-translator-ca-zh-v2"

model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)

sentence = "Benvingut al projecte Aina!"

input_ids = tokenizer(sentence, return_tensors="pt").input_ids
output_ids = model.generate(input_ids, max_length=200, num_beams=5)

generated_translation= tokenizer.decode(output_ids[0], skip_special_tokens=True).strip()
print(generated_translation)
#欢迎来到 Aina 项目！
```


## Limitations and bias
At the time of submission, no measures have been taken to estimate the bias and toxicity embedded in the model. 
However, we are well aware that our models may be biased. We intend to conduct research in these areas in the future, and if completed, this model card will be updated. 

## Training

### Training data

The Catalan-Chinese data collected from the web was a combination of the following datasets:

| Dataset       	| Sentences before cleaning	|
|-------------------|----------------|
| OpenSubtitles  	| 139.300	|
| WikiMatrix | 90.643 |
| Wikipedia 	| 68.623|
| **Total**     	| **298.566** |

94.074.553 sentence pairs of synthetic parallel data were created from the following Spanish-Chinese datasets and English-Chinese datasets:

**Spanish-Chinese:**

| Dataset       	| Sentences before cleaning	|
|-------------------|----------------|
| NLLB 	|24.051.233|
| UNPC | 17.599.223 |
| MultiUN | 9.847.770 |
| OpenSubtitles | 9.319.658 |
| MultiParaCrawl | 3.410.087 |
| MultiCCAligned | 3.006.694 |
| WikiMatrix | 1.214.322 |
| News Commentary | 375.982 |
| Tatoeba | 9.404 |
| **Total**     	| **68.834.373** |

**English-Chinese:**

| Dataset       	| Sentences before cleaning	|
|-------------------|----------------|
| NLLB 	|71.383.325|
| CCAligned | 15.181.415 |
| Paracrawl | 14.170.869|
| WikiMatrix | 2.595.119|
| **Total**     	| **103.330.728** |



### Training procedure

### Data preparation

**Catalan-Chinese parallel data**

The Chinese side of all datasets were first processed using the [Hanzi Identifier](https://github.com/tsroten/hanzidentifier) to detect Traditional Chinese, which was subsequently converted to Simplified Chinese using [OpenCC](https://github.com/BYVoid/OpenCC).

All data was then filtered according to two specific criteria:

- Alignment: sentence level alignments were calculated using [LaBSE](https://huggingface.co/sentence-transformers/LaBSE) and sentence pairs with a score below 0.75 were discarded.

- Language identification: the probability of being the target language was calculated using [Lingua.py](https://github.com/pemistahl/lingua-py) and sentences with a language probability score below 0.5 were discarded.

Next, Spanish data was translated into Catalan using the Aina Project's [Spanish-Catalan machine translation model](https://huggingface.co/projecte-aina/aina-translator-es-ca), while English data was translated into Catalan using the Aina Project's [English-Catalan machine translation model](https://huggingface.co/projecte-aina/aina-translator-en-ca).

The filtered and translated datasets are then concatenated and deduplicated to form a final corpus of 94.187.858.

**Catalan-Chinese Contrastive Preference Optimization dataset**

The CPO dataset is built by comparing the quality of translations across four distinct sources:

- Reference translation: Chinese sentences from Flores test set, Flores devtest set, and NTREX dataset.
- [aina-translator-ca-zh](https://huggingface.co/projecte-aina/aina-translator-ca-zh): A specialized bilingual model for Catalan-Chinese translations.
- Google Translate: A widely-used general-purpose machine translation system.
- OpenAI GPT-4: A large-scale language model capable of performing a wide range of tasks in conversational settings, including high-quality translation.

To evaluate the quality of translations without relying on human annotations, we employ two reference-free evaluation models:

- [Unbabel/wmt23-cometkiwi-da-xxl](https://huggingface.co/Unbabel/wmt23-cometkiwi-da-xxl)
- [Unbabel/XCOMET-XXL](https://huggingface.co/Unbabel/XCOMET-XXL)

These models provide direct assessment scores for each translation. The scores from both models are averaged to determine the relative quality of each translation. Based on this evaluation, the highest-scoring ("chosen") and lowest-scoring ("rejected") translations are identified for each source sentence, forming contrastive pairs. The CPO dataset comprises a total of 4,006 such pairs of "chosen" and "rejected" translations.


#### Training

The training was executed on NVIDIA GPUs utilizing the Hugging Face Transformers framework. 
The model was trained for 245.000 updates.

Following fine-tuning on the M2M100 1.2B model, Contrastive Preference Optimization (CPO) was performed using our CPO dataset and the Hugging Face CPO Trainer. This phase involved 1,500 updates.

## Evaluation

### Variable and metrics

Below are the evaluation results on the Projecte Aina's Catalan-Chinese test set, compared to Google Translate for the CA-ZH direction. The evaluation was conducted using [`tower-eval`](https://github.com/deep-spin/tower-eval) following the standard setting (beam search with beam size 5, limiting the translation length to 200 tokens). We report the following metrics:

- BLEU: Sacrebleu implementation, version:2.4.0
- ChrF: Sacrebleu implementation.
- Comet: Model checkpoint: "Unbabel/wmt22-comet-da".
- Comet-kiwi: Model checkpoint: "Unbabel/wmt22-cometkiwi-da".


### Evaluation results

Below are the evaluation results on the machine translation from Chinese to Catalan compared to [Google Translate](https://translate.google.com/):


#### Projecte Aina's Catalan-Chinese evaluation dataset

|              |   Bleu ↑  |   ChrF ↑ |   Comet ↑ |   Comet-kiwi ↑ |
|:-----------------------|-------:|------:|-------:|--------:|-------------:|---------:|
| aina-translator-zh-ca-v2 |  **28.55** |  **57.64** |    **0.87** |         **0.82** |   
| Google Translate         |  26.84     |   55.7     |    0.86     |         **0.82** | 



## Additional information

### Author
The Language Technologies Unit from Barcelona Supercomputing Center.

### Contact
For further information, please send an email to <langtech@bsc.es>.

### Copyright
Copyright(c) 2023 by Language Technologies Unit, Barcelona Supercomputing Center.

### License
[Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0)

### Funding
This work has been promoted and financed by the Generalitat de Catalunya through the [Aina project](https://projecteaina.cat/).

### Disclaimer

<details>
<summary>Click to expand</summary>

The model published in this repository is intended for a generalist purpose and is available to third parties under a permissive Apache License, Version 2.0. 

Be aware that the model may have biases and/or any other undesirable distortions.

When third parties deploy or provide systems and/or services to other parties using this model (or any system based on it) 
or become users of the model, they should note that it is their responsibility to mitigate the risks arising from its use and, 
in any event, to comply with applicable regulations, including regulations regarding the use of Artificial Intelligence.

In no event shall the owner and creator of the model (Barcelona Supercomputing Center) 
be liable for any results arising from the use made by third parties.

</details>