ELMo-BiDAF

Model Name:*

Description with Markdown (optional):

# Summary

This is an implementation of the BiDAF model with ELMo embeddings. The basic layout is pretty simple: encode words as a combination of word embeddings and a character-level encoder, pass the word representations through a bi-LSTM/GRU, use a matrix of attentions to put question information into the passage word representations (this is the only part that is at all non-standard), pass this through another few layers of bi-LSTMs/GRUs, and do a softmax over span start and span end.

[Explore live Reading Comprehension demo at AllenNLP](https://demo.allennlp.org/reading-comprehension/bidaf-elmo).

## How do I load this model?

```python
from allennlp_models.pretrained import load_predictor
predictor = load_predictor("rc-bidaf-elmo")
```

### Getting predictions

```python
question = "Who graduated in 1936?"
passage = ("In 1932, Shannon entered the University of Michigan,"
    " where he was introduced to the work of George Boole. He"
    " graduated in 1936 with two bachelor's degrees: one in"
    " electrical engineering and the other in mathematics."
)
preds = predictor.predict(question, passage)
print(preds["best_span_str"])
# prints: George Boole
```

You can also get predictions using allennlp command line interface:

```shell
echo '{"question": "Who graduated in 1936?", "passage": "In 1932, Shannon entered the University..."}' | \
    allennlp predict https://storage.googleapis.com/allennlp-public-models/bidaf-elmo.2021-02-11.tar.gz -
```

## How do I evaluate this model?
To evaluate the model on SQuAD dev set run:

```shell
allennlp evaluate https://storage.googleapis.com/allennlp-public-models/bidaf-elmo.2021-02-11.tar.gz \
    https://s3-us-west-2.amazonaws.com/allennlp/datasets/squad/squad-dev-v1.1.json
```

## How do I train this model?

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

```shell
allennlp train bidaf_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
@article{Seo2017BidirectionalAF,
 author = {Minjoon Seo and Aniruddha Kembhavi and Ali Farhadi and Hannaneh Hajishirzi},
 journal = {ArXiv},
 title = {Bidirectional Attention Flow for Machine Comprehension},
 volume = {abs/1611.01603},
 year = {2017}
}
```

Paper:*

Code URL (optional):

Epochs	20
Dropout	0.2
Batch Size	40

Attached motifs:

CONVOLUTION

HIGHWAY LAYER

LSTM

RELU

ELMO

DROPOUT

LINEAR LAYER

CONVOLUTION

BENCHMARK	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
SQuAD1.1 dev	ELMo-BiDAF	EM	71	# 2
		F1	80	# 2

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

Question Answering on SQuAD1.1 dev

Question Answering

Training Techniques	Adam
Architecture	Convolution, Dropout, ELMo, Highway Layer, LSTM, Linear Layer, ReLU
Epochs	20
Dropout	0.2
Batch Size	40
SHOW MORE
SHOW LESS