pierluigic/xl-lexeme

This model is based on sentence-transformers: It maps target word in sentences to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Usage (WordTransformer)

Install the library:

git clone [email protected]:pierluigic/xl-lexeme.git
cd xl-lexeme
pip3 install .

Then you can use the model like this:

from WordTransformer import WordTransformer, InputExample

model = WordTransformer('pierluigic/xl-lexeme')
examples = InputExample(texts="the quick fox jumps over the lazy dog", positions=[10,13])
fox_embedding = model.encode(examples) #The embedding of the target word "fox"

Training

The model was trained with the parameters:

DataLoader:

torch.utils.data.dataloader.DataLoader of length 16531 with parameters:

{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss:

sentence_transformers.losses.ContrastiveLoss.ContrastiveLoss with parameters:

{'distance_metric': 'SiameseDistanceMetric.COSINE_DISTANCE', 'margin': 0.5, 'size_average': True}

Parameters of the fit()-Method:

{
    "epochs": 10,
    "evaluation_steps": 4132,
    "evaluator": "sentence_transformers.evaluation.SequentialEvaluator.SequentialEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
    "optimizer_params": {
        "lr": 1e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 16531.0,
    "weight_decay": 0.0
}

Full Model Architecture

SentenceTransformerTarget(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

Citing & Authors

@inproceedings{cassotti-etal-2023-xl,
    title = "{XL}-{LEXEME}: {W}i{C} Pretrained Model for Cross-Lingual {LEX}ical s{EM}antic chang{E}",
    author = "Cassotti, Pierluigi  and
      Siciliani, Lucia  and
      DeGemmis, Marco  and
      Semeraro, Giovanni  and
      Basile, Pierpaolo",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-short.135",
    pages = "1577--1585"
}