Constituency Parser with ELMo embeddings

Model Name:*

Description with Markdown (optional):

# Summary

This is an implementation of a minimal neural model for constituency parsing based on an independent scoring of labels and spans. This `SpanConstituencyParser` simply encodes a sequence of text with a stacked `Seq2SeqEncoder`, extracts span representations using a `SpanExtractor`, and then predicts a label for each span in the sequence. These labels are non-terminal nodes in a constituency parse tree, which we then greedily reconstruct. The model uses ELMo embeddings, which are completely character-based and improves single model performance from 92.6 F1 to 94.11 F1 on the Penn Treebank, a 20% relative error reduction.

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

## How do I load this model?

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

### Getting predictions

```python
sentence = "One morning I shot an elephant in my pajamas."
preds = predictor.predict(sentence)
print(preds["trees"])
# prints:
# (S (NP (CD One) (NN morning)) (NP (PRP I)) (VP (VBD shot) (NP (DT an) (NN elephant)) (PP (IN in) (NP (PRP$ my) (NNS pajamas)))) (. .))
```

You can also get predictions using allennlp command line interface:

```shell
echo '{"sentence": "One morning I shot an elephant in my pajamas."}' | \
    allennlp predict https://storage.googleapis.com/allennlp-public-models/elmo-constituency-parser-2020.02.10.tar.gz -
```

## How do I train this model?

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

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

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

## Citation

```bibtex
@inproceedings{Joshi2018ExtendingAP,
 author = {V. Joshi and Matthew E. Peters and Mark Hopkins},
 booktitle = {ACL},
 title = {Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples},
 year = {2018}
}
```

Paper:*

Code URL (optional):

LR	1
Epochs	150
Encoder Type	LSTM
Encoder Layers	2
Encoder Input Size	1074
Encoder Hidden Size	250
Encoder Bidirectional	True

Attached motifs:

FEEDFORWARD NETWORK

LSTM

ELMO

CONVOLUTION

HIGHWAY LAYER

RELU

DROPOUT

LINEAR LAYER

FEEDFORWARD NETWORK

Constituency Parser with ELMo embeddings

allenai / allennlp

Summary

How do I load this model?

Getting predictions

How do I train this model?

Citation

Results

Constituency Parsing on Penn Treebank

Constituency Parsing

Training Techniques	AdaDelta
Architecture	Convolution, Dropout, ELMo, Feedforward Network, Highway Layer, LSTM, Linear Layer, ReLU
LR	1
Epochs	150
Encoder Type	LSTM
Encoder Layers	2
Encoder Input Size	1074
Encoder Hidden Size	250
Encoder Bidirectional	True
SHOW MORE
SHOW LESS