---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- word-similarity
- transformers
widget:
- source_sentence: "Provide a large table; this is a horizontal <t>plane</t>, and will represent the ground plane, viz."
  sentences:
    - "The President's <t>plane</t> landed at Goose Bay at 9:03 p.m."
    - "any line joining two points on a <t>plane</t> lies wholly on that plane"
    - "the flight was delayed due to trouble with the <t>plane</t>"
  example_title: "plane (en)"
- source_sentence: "La <t>radice</t> del problema non è nota"
  sentences:
    - "il liquore è fatto dalle <t>radici</t>  di liquirizia"
    - "La <t>radice</t>  di 2 è 4."
    - "occorre pertanto trasformare la società alla <t>radice</t>"
  example_title: "radice (it)"
---

# pierluigic/xl-lexeme

This model is based on [sentence-transformers](https://www.SBERT.net): It maps target word in sentences to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.

<!--- Describe your model here -->

## Usage (WordTransformer)

Install the library:

```
git clone git@github.com:pierluigic/xl-lexeme.git
cd xl-lexeme
pip3 install .
```

Then you can use the model like this:

```python
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"
}
```