Deep Biaffine Attention for Neural Dependency Parsing

Model Name:*

Description with Markdown (optional):

# Summary

This dependency parser follows the model of [Deep Biaffine Attention for Neural Dependency Parsing (Dozat and Manning, 2016)](https://api.semanticscholar.org/CorpusID:7942973).

Word representations are generated using a bidirectional LSTM, followed by separate biaffine classifiers for pairs of words, predicting whether a directed arc exists between the two words and the dependency label the arc should have. Decoding can either be done greedily, or the optimal Minimum Spanning Tree can be decoded using Edmond's algorithm by viewing the dependency tree as a MST on a fully connected graph, where nodes are words and edges are scored dependency arcs.

[Explore live Dependency Parsing demo at AllenNLP](https://demo.allennlp.org/dependency-parsing/dependency-parser).

## How do I load this model?

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

### Getting predictions

```python
sentence = "The dog was chased by the cat."
preds = predictor.predict(sentence)
words = preds["words"]
poss = preds["pos"]
deps = preds["predicted_dependencies"]
for word, pos, dep in zip(words, poss, deps):
    print(f"{word} ({pos}) [{dep}]")
# prints:
# The (DET) [det]
# dog (NOUN) [nsubjpass]
# was (AUX) [auxpass]
# chased (VERB) [root]
# by (ADP) [prep]
# the (DET) [det]
# cat (NOUN) [pobj]
# . (PUNCT) [punct]
```

You can also get predictions using allennlp command line interface:

```shell
echo '{"sentence": "The dog was chased by the cat."}' | \
    allennlp predict https://storage.googleapis.com/allennlp-public-models/biaffine-dependency-parser-ptb-2020.04.06.tar.gz -
```

## How do I train this model?

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

```shell
allennlp train dependency_parser.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{Dozat2017DeepBA,
 author = {Timothy Dozat and Christopher D. Manning},
 journal = {ArXiv},
 title = {Deep Biaffine Attention for Neural Dependency Parsing},
 volume = {abs/1611.01734},
 year = {2017}
}
```

Paper:*

Code URL (optional):

Epochs	50
Dropout	0.3
Batch Size	128
Encoder Type	stacked_bidirectional_lstm
Encoder Layers	3
Encoder Input Size	200
Encoder Hidden Size	400

DROPOUT

BENCHMARK	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Penn Treebank	Deep Biaffine Attention for Neural Dependency Parsing	UAS	95.57	# 1
		LAS	94.44	# 1

Deep Biaffine Attention for Neural Dependency Parsing

allenai / allennlp

Summary

How do I load this model?

Getting predictions

How do I train this model?

Citation

Results

Dependency Parsing on Penn Treebank

Dependency Parsing

Architecture	Dropout, ELU, Feedforward Network, Linear Layer, Variational Dropout
Epochs	50
Dropout	0.3
Batch Size	128
Encoder Type	stacked_bidirectional_lstm
Encoder Layers	3
Encoder Input Size	200
Encoder Hidden Size	400
SHOW MORE
SHOW LESS