|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: iva_mt_wslot-m2m100_418M-0.1.0 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# iva_mt_wslot-m2m100_418M-0.1.0 en-pl |
|
|
|
This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the [iva_mt_wslot](https://huggingface.co/datasets/cartesinus/iva_mt_wslot) dataset. |
|
|
|
|
|
It achieves the following results: |
|
1) On the test set (iva_mt): |
|
- Bleu (plain text): 39.1560 |
|
- Bleu (with slots): 63.8767 |
|
- Baseline m2m100-418M (plain text): TBD |
|
|
|
2) WMT20 (en2pl): |
|
- Bleu (lowercased, tags removed): 15.0863 (for reference WMT20 submission systems in en-pl direction had between 25 and 30 bleu) |
|
- Baseline m2m100-418M (plain text): TBD |
|
|
|
4) On the evaluation set: |
|
- Bleu: 61.6249 |
|
|
|
3) On the training set (to see how it adjusted to train): |
|
- Bleu (plain text): 70.5597 |
|
- Bleu (with slots): 93.8200 |
|
|
|
Bleu was measured with (sacrebleu)[https://github.com/mjpost/sacrebleu] library. |
|
|
|
## Model description, intended uses & limitations |
|
|
|
Model is biased towards virtual assistant (IVA) sentences in prediction/translation. These sentences are short, most of them are short, imperatives. Both of this facts |
|
can be observed in above results. WMT results are very low while in-domain test is very high. One thing that needs to be mentioned is that BLEU is not particulary good |
|
metric to evaluate IVA sentences due to their length and it should be evalued with other metrices (e.g. [GLEU](https://aclanthology.org/P15-2097.pdf)). |
|
|
|
This model will most probably force IVA translations on your text. As long as sentences that you are translating are more or less similar to massive and leyzer domains it |
|
can work. If you will translate domains unseen in either of them results might drop significantly to the point where baseline m2m100-418M will be better than this model. |
|
|
|
This model will generate tags in output even if there is not tag in input sentence. Frequency of this depends on input text. When testing IVA utterances this occurs |
|
between 3 and 5% of all cases. When WMT20 was translated it happened in % cases (input text was from News domain). |
|
This is not very severe and can be fixed easily in post-processing (something like `sed 's/<[a-z]>//g'` should be enough in most cases). |
|
|
|
Translations with slots very often differ from same sentences when slots are removed. This is quite frequent and it happens between 30 and 50% of translated utterances. |
|
For example there will be a difference between "is it raining in barcelona" and "is it raining in <a>barcelona<a>". In second case model will more likely localize name of |
|
city to some Polish name (here Lublin, because such city was given in Massive train set). This might be useful if you want to generate more variants. |
|
|
|
## How to use |
|
|
|
First please make sure to install `pip install transformers`. First download model: |
|
|
|
```python |
|
from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer |
|
import torch |
|
|
|
def translate(input_text, lang): |
|
input_ids = tokenizer(input_text, return_tensors="pt") |
|
generated_tokens = model.generate(**input_ids, forced_bos_token_id=tokenizer.get_lang_id(lang)) |
|
return tokenizer.batch_decode(generated_tokens, skip_special_tokens=True) |
|
|
|
model_name = "cartesinus/iva_mt_wslot-m2m100_418M-0.1.0" |
|
tokenizer = M2M100Tokenizer.from_pretrained(model_name, src_lang="en", tgt_lang="pl") |
|
model = M2M100ForConditionalGeneration.from_pretrained(model_name) |
|
``` |
|
|
|
Then you can translate either plan text like this: |
|
```python |
|
print(translate("set the temperature on my thermostat", "pl")) |
|
``` |
|
or you can translate with slot annotations that will be restored in tgt language: |
|
```python |
|
print(translate("wake me up at <a>nine am<a> on <b>friday<b>", "pl")) #translation: obudź mnie o <a>piątej rano<a> <b>w tym tygodniu<b> |
|
``` |
|
Limitations of translation with slot transfer: |
|
1) Annotated words must be placed between semi-xml tags like this "this is <a>example<a>" |
|
2) There is no closing tag for example "<\a>" in above example - this is done on purpose to ommit problems with backslash escape |
|
3) If sentence consists of more than one slot then simply use next alphabet letter. For example "this is <a>example<a> with more than <b>one<b> slot" |
|
4) Please do not add space before first or last annotated word because this particular model was trained this way and it most probably will lower it's results |
|
|
|
|
|
## Training and evaluation data |
|
|
|
## Dataset Composition (en-pl) |
|
| Corpus | Train | Dev | Test | |
|
|----------------------------------------------------------------------|--------|-------|-------| |
|
| [Massive 1.1](https://huggingface.co/datasets/AmazonScience/massive) | 11514 | 2033 | 2974 | |
|
| [Leyzer 0.2.0](https://github.com/cartesinus/leyzer/tree/0.2.0) | 3974 | 701 | 1380 | |
|
| [OpenSubtitles from OPUS](https://opus.nlpl.eu/OpenSubtitles-v1.php) | 2329 | 411 | 500 | |
|
| [KDE from OPUS](https://opus.nlpl.eu/KDE4.php) | 1154 | 241 | 241 | |
|
| [CCMatrix from Opus](https://opus.nlpl.eu/CCMatrix.php) | 1096 | 232 | 237 | |
|
| [Ubuntu from OPUS](https://opus.nlpl.eu/Ubuntu.php) | 281 | 60 | 59 | |
|
| [Gnome from OPUS](https://opus.nlpl.eu/GNOME.php) | 14 | 3 | 3 | |
|
| *total* | 20362 | 3681 | 5394 | |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:| |
|
| 0.0178 | 1.0 | 5091 | 0.0171 | 57.4439 | 21.1396 | |
|
| 0.013 | 2.0 | 10182 | 0.0159 | 58.886 | 21.2285 | |
|
| 0.0091 | 3.0 | 15273 | 0.0157 | 60.159 | 21.1222 | |
|
| 0.0073 | 4.0 | 20364 | 0.0159 | 60.5893 | 21.1212 | |
|
| 0.0054 | 5.0 | 25455 | 0.0161 | 60.6484 | 21.0679 | |
|
| 0.004 | 6.0 | 30546 | 0.0166 | 61.5283 | 21.0875 | |
|
| 0.0031 | 7.0 | 35637 | 0.0169 | 61.0439 | 21.1562 | |
|
| 0.0024 | 8.0 | 40728 | 0.0172 | 61.9427 | 21.2203 | |
|
| 0.0018 | 9.0 | 45819 | 0.0175 | 61.7325 | 21.1478 | |
|
| 0.0014 | 10.0 | 50910 | 0.0176 | 61.6249 | 21.157 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
