explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-24 16:24:16 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of ssh://github.com/explosion/spaCy

Browse Source
This commit is contained in:
Matthew Honnibal 2016-11-01 12:26:15 +01:00
commit 41b7014c70
2 changed files with 24 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
examples/keras_parikh_entailment/README.md
View File

@ -1,14 +1,14 @@
<a href="https://explosion.ai"><img src="https://explosion.ai/assets/img/logo.svg" width="125" height="125" align="right" /></a>
# A Decomposable Attention Model for Natural Language Inference
# A decomposable attention model for Natural Language Inference
**by Matthew Honnibal, [@honnibal](https://github.com/honnibal)**
This directory contains an implementation of entailment prediction model described
This directory contains an implementation of the entailment prediction model described
by [Parikh et al. (2016)](https://arxiv.org/pdf/1606.01933.pdf). The model is notable
for its competitive performance with very few parameters.
The model is implemented using [Keras](https://keras.io/) and [spaCy](https://spacy.io).
Keras is used to build and train the network, while spaCy is used to load
Keras is used to build and train the network. spaCy is used to load
the [GloVe](http://nlp.stanford.edu/projects/glove/) vectors, perform the
feature extraction, and help you apply the model at run-time. The following
demo code shows how the entailment model can be used at runtime, once the
@ -35,20 +35,16 @@ lots of ways to extend the model.
## What's where
* `keras_parikh_entailment/__main__.py`: The script that will be executed.
Defines the CLI, the data reading, etc — all the boring stuff.
* `keras_parikh_entailment/spacy_hook.py`: Provides a class `SimilarityShim`
that lets you use an arbitrary function to customize spaCy's
`doc.similarity()` method. Instead of the default average-of-vectors algorithm,
when you call `doc1.similarity(doc2)`, you'll get the result of `your_model(doc1, doc2)`.
* `keras_parikh_entailment/keras_decomposable_attention.py`: Defines the neural network model.
This part knows nothing of spaCy --- its ordinary Keras usage.
| File | Description |
| --- | --- |
| `__main__.py` | The script that will be executed. Defines the CLI, the data reading, etc — all the boring stuff. |
| `spacy_hook.py` | Provides a class `SimilarityShim` that lets you use an arbitrary function to customize spaCy's `doc.similarity()` method. Instead of the default average-of-vectors algorithm, when you call `doc1.similarity(doc2)`, you'll get the result of `your_model(doc1, doc2)`. |
| `keras_decomposable_attention.py` | Defines the neural network model. |
## Setting up
First, install keras, spaCy and the spaCy English models (about 1GB of data):
First, install [Keras](https://keras.io/), [spaCy](https://spacy.io) and the spaCy
English models (about 1GB of data):
```bash
pip install keras spacy
@ -56,11 +52,11 @@ python -m spacy.en.download
```
You'll also want to get keras working on your GPU. This will depend on your
set up, so you're mostly on your own for this step. If you're using AWS, try the NVidia
AMI. It made things pretty easy.
set up, so you're mostly on your own for this step. If you're using AWS, try the
[NVidia AMI](https://aws.amazon.com/marketplace/pp/B00FYCDDTE). It made things pretty easy.
Once you've installed the dependencies, you can run a small preliminary test of
the keras model:
the Keras model:
```bash
py.test keras_parikh_entailment/keras_decomposable_attention.py
@ -69,14 +65,12 @@ py.test keras_parikh_entailment/keras_decomposable_attention.py
This compiles the model and fits it with some dummy data. You should see that
both tests passed.
Finally, download the Stanford Natural Language Inference corpus.
Source: http://nlp.stanford.edu/projects/snli/
Finally, download the [Stanford Natural Language Inference corpus](http://nlp.stanford.edu/projects/snli/).
## Running the example
You can run the `keras_parikh_entailment/` directory as a script, which executes the file
`keras_parikh_entailment/__main__.py`. The first thing you'll want to do is train the model:
[`keras_parikh_entailment/__main__.py`](__main__.py). The first thing you'll want to do is train the model:
```bash
python keras_parikh_entailment/ train <your_model_dir> <train_directory> <dev_directory>
@ -95,4 +89,5 @@ you how run-time usage will eventually look.
## Getting updates
We should have the blog post explaining the model ready before the end of the week. To get
notified when it's published, you can either the follow me on Twitter, or subscribe to our mailing list.
notified when it's published, you can either the follow me on [Twitter](https://twitter.com/honnibal),
or subscribe to our [mailing list](http://eepurl.com/ckUpQ5).

8
website/docs/usage/_data.json
View File

@ -214,6 +214,12 @@
"author": "Matthew Honnibal",
"tags": [ "keras", "sentiment" ]
},
"A decomposable attention model for Natural Language Inference": {
"url": "https://github.com/explosion/spaCy/tree/master/examples/keras_parikh_entailment",
"author": "Matthew Honnibal",
"tags": [ "keras", "similarity" ]
},
"Using the German model": {
"url": "https://explosion.ai/blog/german-model",
"author": "Wolfgang Seeker",
@ -263,7 +269,7 @@
"tags": [ "big data" ]
},
"Inventory count": {
"url": "https://github.com/explosion/spaCy/tree/master/examples/InventoryCount",
"url": "https://github.com/explosion/spaCy/tree/master/examples/inventory_count",
"author": "Oleg Zd"
},
"Multi-word matches": {