SRL BERT

Model Name:*

Description with Markdown (optional):

# Summary

An implementation of a BERT based model [(Shi et al, 2019)](https://paperswithcode.com/paper/simple-bert-models-for-relation-extraction) 
with some modifications (no additional parameters apart from a linear classification layer).

[Explore live Semantic Role Labeling demo at AllenNLP](https://demo.allennlp.org/semantic-role-labeling/semantic-role-labeling).

## How do I load this model?

```python
from allennlp_models.pretrained import load_predictor
predictor = load_predictor("structured-prediction-srl-bert")
```

### Getting predictions

```python
sentence = "John broke the window with a rock."
preds = predictor.predict(sentence)
print(preds["verbs"][0]["description"])
# prints:
# [ARG0: John] [V: broke] [ARG1: the window] [ARG2: with a rock] .
```

You can also get predictions using allennlp command line interface:

```shell
echo '{"sentence": "John broke the window with a rock."}' | \
    allennlp predict https://storage.googleapis.com/allennlp-public-models/structured-prediction-srl-bert.2020.12.15.tar.gz -
```

## How do I train this model?

To train this model you can use `allennlp` CLI tool and the configuration file [bert_base_srl.jsonnet](https://raw.githubusercontent.com/allenai/allennlp-models/v2.1.0/training_config/structured_prediction/bert_base_srl.jsonnet):

```shell
allennlp train bert_base_srl.jsonnet -s output_dir
```

See the [AllenNLP Training and prediction](https://guide.allennlp.org/training-and-prediction#2) guide for more details.

## Citation

```bibtex
@article{Shi2019SimpleBM,
 author = {Peng Shi and Jimmy Lin},
 journal = {ArXiv},
 title = {Simple BERT Models for Relation Extraction and Semantic Role Labeling},
 volume = {abs/1904.05255},
 year = {2019}
}
```

Paper:*

Code URL (optional):

LR	0.00005
Epochs	15
Batch Size	32

LAYER NORMALIZATION

allenai / allennlp

Summary

How do I load this model?

Getting predictions

How do I train this model?

Citation

Results

Semantic Role Labeling on OntoNotes

Semantic Role Labeling

Training Techniques	AdamW
Architecture	BERT, Dropout, Layer Normalization, Linear Layer, Tanh
LR	0.00005
Epochs	15
Batch Size	32
SHOW MORE
SHOW LESS