Pretrained multilingual language model using a masked language modeling (MLM) objective. Details about the model here.
This model, unlike other ALBERT models, is cased: it does make a difference between french and French.
Model description
mALBERT is a transformers model pretrained on 16Go of French Wikipedia in a self-supervised fashion. This means it
was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of
publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
was pretrained with two objectives:
Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run
the entire masked sentence through the model and has to predict the masked words. This is different from traditional
recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like
GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the
sentence.
Sentence Ordering Prediction (SOP): mALBERT uses a pretraining loss based on predicting the ordering of two consecutive segments of text.
This way, the model learns an inner representation of the languages that can then be used to extract features
useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard
classifier using the features produced by the mALBERT model as inputs.
mALBERT is particular in that it shares its layers across its Transformer. Therefore, all layers have the same weights. Using repeating layers results in a small memory footprint, however, the computational cost remains similar to a BERT-like architecture with the same number of hidden layers as it has to iterate through the same number of (repeating) layers.
This is the second version of the base model.
This model has the following configuration:
12 repeating layers
128 embedding dimension
768 hidden dimension
12 attention heads
11M parameters
32k of vocabulary size
Intended uses & limitations
You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
be fine-tuned on a downstream task. See the model hub to look for
fine-tuned versions on a task that interests you.
Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked)
to make decisions, such as sequence classification, token classification or question answering. For tasks such as text
generation you should look at model like GPT2.
How to use
Here is how to use this model to get the features of a given text in PyTorch:
python
1from transformers import AlbertTokenizer, AlbertModel
2tokenizer = AlbertTokenizer.from_pretrained('cservan/multilingual-albert-base-cased-32k')3model = AlbertModel.from_pretrained("cservan/multilingual-albert-base-cased-32k")4text ="Remplacez-moi par le texte en français que vous souhaitez."5encoded_input = tokenizer(text, return_tensors='pt')6output = model(**encoded_input)
and in TensorFlow:
python
1from transformers import AlbertTokenizer, TFAlbertModel
2tokenizer = AlbertTokenizer.from_pretrained('cservan/multilingual-albert-base-cased-32k')3model = TFAlbertModel.from_pretrained("cservan/multilingual-albert-base-cased-32k")4text ="Remplacez-moi par le texte en français que vous souhaitez."5encoded_input = tokenizer(text, return_tensors='tf')6output = model(encoded_input)
Training data
The mALBERT model was pretrained on 13go of Multiligual Wikipedia (excluding lists, tables and
headers).
Training procedure
Preprocessing
The texts are lowercased and tokenized using SentencePiece and a vocabulary size of 128,000. The inputs of the model are
then of the form:
[CLS] Sentence A [SEP] Sentence B [SEP]
Training
The mALBERT procedure follows the BERT setup.
The details of the masking procedure for each sentence are the following:
15% of the tokens are masked.
In 80% of the cases, the masked tokens are replaced by [MASK].
In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
In the 10% remaining cases, the masked tokens are left as is.
Tools
The tools used to pre-train the model are available here
Evaluation results
When fine-tuned on downstream tasks, the ALBERT models achieve the following results:
Slot-filling:
Models ⧹ Tasks
MMNLU
MultiATIS++
CoNLL2003
MultiCoNER
SNIPS
MEDIA
EnALBERT
N/A
N/A
89.67 (0.34)
42.36 (0.22)
95.95 (0.13)
N/A
FrALBERT
N/A
N/A
N/A
N/A
N/A
81.76 (0.59)
mALBERT-128k
65.81 (0.11)
89.14 (0.15)
88.27 (0.24)
46.01 (0.18)
91.60 (0.31)
83.15 (0.38)
mALBERT-64k
65.29 (0.14)
88.88 (0.14)
86.44 (0.37)
44.70 (0.27)
90.84 (0.47)
82.30 (0.19)
mALBERT-32k
64.83 (0.22)
88.60 (0.27)
84.96 (0.41)
44.13 (0.39)
89.89 (0.68)
82.04 (0.28)
Classification task:
Models ⧹ Tasks
MMNLU
MultiATIS++
SNIPS
SST2
mALBERT-128k
72.35 (0.09)
90.58 (0.98)
96.84 (0.49)
34.66 (1.46)
mALBERT-64k
71.26 (0.11)
90.97 (0.70)
96.53 (0.44)
34.64 (1.02)
mALBERT-32k
70.76 (0.11)
90.55 (0.98)
96.49 (0.45)
34.18 (1.64)
BibTeX entry and citation info
bibtex
1@inproceedings{servan2024mALBERT,
2 author = {Christophe Servan and
3 Sahar Ghannay and
4 Sophie Rosset},
5 booktitle = {the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
6 title = {{mALBERT: Is a Compact Multilingual BERT Model Still Worth It?}},
7 year = {2024},
8 address = {Torino, Italy},
9 month = may,
10}
