https://github.com/riccorl/transformer-srl
Reimplementation of a BERT based model (Shi et al, 2019), currently the state-of-the-art for English SRL. This model implements also predicate disambiguation.
https://github.com/riccorl/transformer-srl
allennlp bert conll2012 dataset labeling natural-language-processing nlp propbank pytorch role semantic semantic-role-labeling shi span srl srl-annotations srltagger transformer transformers verbatlas
Last synced: 2 months ago
JSON representation
Reimplementation of a BERT based model (Shi et al, 2019), currently the state-of-the-art for English SRL. This model implements also predicate disambiguation.
- Host: GitHub
- URL: https://github.com/riccorl/transformer-srl
- Owner: Riccorl
- Created: 2020-07-18T08:48:21.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2022-03-19T10:47:53.000Z (about 3 years ago)
- Last Synced: 2025-04-14T04:16:38.999Z (2 months ago)
- Topics: allennlp, bert, conll2012, dataset, labeling, natural-language-processing, nlp, propbank, pytorch, role, semantic, semantic-role-labeling, shi, span, srl, srl-annotations, srltagger, transformer, transformers, verbatlas
- Language: Perl
- Homepage:
- Size: 1.21 MB
- Stars: 70
- Watchers: 6
- Forks: 9
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- Citation: CITATION.cff
Awesome Lists containing this project
README
[](https://github.com/psf/black)
# Semantic Role Lableing with BERT
Semantic Role Labeling based on [AllenNLP implementation](https://demo.allennlp.org/semantic-role-labeling) of [Shi et al, 2019](https://arxiv.org/abs/1904.05255). Can be trained using both PropBank and [VerbAtlas](http://verbatlas.org/) inventories and implements also the predicate disambiguation task, in addition to arguments identification and disambiguation.
## How to use
Install the library
```bash
pip install transformer-srl
```
## Pre-trained model
You can also use a pre-trained model. To use it, first install the correct version of `transformer-srl`:
```bash
pip install transformer-srl==2.4.6
```
then download the pretrained model `srl_bert_base_conll2012.tar.gz` from [here](https://www.dropbox.com/s/4tes6ypf2do0feb/srl_bert_base_conll2012.tar.gz).
| File | Model | Version | F1 Argument | F1 Predicate |
| :---: | :---: | :---: | :---: | :---: |
| srl_bert_base_conll2012.tar.gz | `bert-base-cased` | 2.4.6 | 86.0 | 95.5 |
#### CLI
```bash
echo '{"sentence": "Did Uriah honestly think he could beat the game in under three hours?"}' | \
allennlp predict path/to/srl_bert_base_conll2012.tar.gz - --include-package transformer_srl
```
#### Inside Python Code
```python
from transformer_srl import dataset_readers, models, predictors
predictor = predictors.SrlTransformersPredictor.from_path("path/to/srl_bert_base_conll2012.tar.gz, "transformer_srl")
predictor.predict(
sentence="Did Uriah honestly think he could beat the game in under three hours?"
)
```
## Infos
- Language Model: BERT
- Dataset: CoNLL 2012
### Results with VerbAtlas
With `bert-base-cased`:
```
# Dev set
- F1 arguments 87.6
- F1 predicates 95.5
# Test set
- F1 arguments x
- F1 predicates x
```
With `bert-base-multilingual-cased`:
```
# Dev set
- F1 arguments 86.2
- F1 predicates 94.2
# Test set
- F1 arguments 86.1
- F1 predicates 94.9
```
### To-Dos
- [x] Works with both PropBank and VerbAtlas (infer inventory from dataset reader)
- [ ] Compatibility with all models from Huggingface's Transformers.
- Now works only with models that accept 1 as token type id
- [ ] Predicate identification (without using spacy)