Fine Grained Named Entity Recognition

Model Name:*

Description with Markdown (optional):

# Summary

This model identifies a broad range of 16 semantic types in the input text. It is a reimplementation of Lample (2016) and uses a biLSTM with a CRF layer, character embeddings and ELMo embeddings.

[Explore live Named Entity Recognition demo at AllenNLP](https://demo.allennlp.org/named-entity-recognition/fine-grained-ner).

## How do I load this model?

```python
from allennlp_models.pretrained import load_predictor
predictor = load_predictor("tagging-fine-grained-crf-tagger")
```

### Getting predictions

```python
sentence = "Jobs and Wozniak cofounded Apple in 1976."
preds = predictor.predict(sentence)
for word, tag in zip(preds["words"], preds["tags"]):
    print(word, tag)
# prints:
# Jobs O
# and O
# Wozniak U-PERSON
# cofounded O
# Apple U-ORG
# in O
# 1976 U-DATE
# . O
```

You can also get predictions using allennlp command line interface:

```shell
echo '{"sentence": "Jobs and Wozniak cofounded Apple in 1976."}' | \
    allennlp predict https://storage.googleapis.com/allennlp-public-models/fine-grained-ner.2021-02-11.tar.gz -
```

## How do I evaluate this model?
To evaluate the model on Ontonotes 5.0 run:

```shell
allennlp evaluate https://storage.googleapis.com/allennlp-public-models/fine-grained-ner.2021-02-11.tar.gz \
    /path/to/dataset
```

## How do I train this model?

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

```shell
allennlp train fine-grained-ner.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{Lample2016NeuralAF,
 author = {Guillaume Lample and Miguel Ballesteros and Sandeep Subramanian and K. Kawakami and Chris Dyer},
 journal = {ArXiv},
 title = {Neural Architectures for Named Entity Recognition},
 volume = {abs/1603.01360},
 year = {2016}
}
```

Paper:*

Code URL (optional):

LR	0.001
Epochs	30
Dropout	0.5
Batch Size	64
Encoder Type	stacked_bidirectional_lstm
Encoder Layers	2
Encoder Input Size	1202
Encoder Hidden Size	200

Attached motifs:

DROPOUT

LINEAR LAYER

VARIATIONAL DROPOUT

FEEDFORWARD NETWORK

LSTM

CRF

ELMO

CONVOLUTION

HIGHWAY LAYER

DROPOUT

Fine Grained Named Entity Recognition

allenai / allennlp

Summary

How do I load this model?

Getting predictions

How do I evaluate this model?

How do I train this model?

Citation

Results

Named Entity Recognition on Ontonotes v5 (English)

Named Entity Recognition

Architecture	CRF, Convolution, Dropout, ELMo, Feedforward Network, Highway Layer, LSTM, Linear Layer, Tanh, Variational Dropout
LR	0.001
Epochs	30
Dropout	0.5
Batch Size	64
Encoder Type	stacked_bidirectional_lstm
Encoder Layers	2
Encoder Input Size	1202
Encoder Hidden Size	200
SHOW MORE
SHOW LESS