This repo hosts the code and a presentation associated with O'Reilly article, "Textual entailment with TensorFlow: Using neural networks to explore natural language," published on July 17, 2017.
This article serves as an introduction to textual entailment, a simple natural language processing machine learning task, and guides you through creating a model that will accomplish this task. In natural language processing, the task of textual entailment attempts to answer the question of whether, given one text that is accepted as truth, another text is true, false, or indeterminable. The article, with the help of the code contained within this notebook, uses textual entailment as a practical example of the uses of word vectorization, recurrence in neural networks, LSTMs, and dropout as a regularization method.
In order to run this notebook, you'll need to install TensorFlow v1.0, Jupyter, NumPy, and Matplotlib.
The notebook also uses TQDM to display friendly progress bars during training.
Note: The first time you run this notebook, it will download the SNLI and GloVe datasets from Stanford University. Together these total just under 1 gigabyte of data and may take several minutes to download, depending on the speed of your connection. After the first run, the notebook will use local copies of the datasets cached on your machine.
There are two easy ways to install these libraries and their dependencies:
-
Download and unzip this entire repo from GitHub, either interactively, or by entering
git clone https://github.com/Steven-Hewitt/Entailment-with-Tensorflow.git
-
Open your terminal and use
cd
to navigate into the top directory of the repo on your machine -
To build the Dockerfile, enter
docker build -t entailment_dockerfile -f dockerfile .
If you get a permissions error on running this command, you may need to run it with
sudo
:sudo docker build -t entailment_dockerfile -f dockerfile .
-
Run Docker from the Dockerfile you've just built
docker run -it -p 8888:8888 -p 6006:6006 entailment_dockerfile bash
or
sudo docker run -it -p 8888:8888 -p 6006:6006 entailment_dockerfile bash
if you run into permission problems.
-
Launch Jupyter by entering
jupyter notebook
and, using your browser, navigate to the URL shown in the terminal output (usually http://localhost:8888/)
NumPy can be tricky to install manually, so we recommend using the managed Anaconda Python distribution, which includes NumPy, Matplotlib, and Jupyter in a single installation. The Docker-based method above is much easier, but if you have a compatible NVIDIA GPU, manual installation makes it possible to use GPU acceleration to speed up training.
-
Follow the installation instructions for Anaconda Python. We recommend using Python 3.6.
-
Follow the platform-specific TensorFlow installation instructions. Be sure to follow the "Installing with Anaconda" process, and create a Conda environment named
tensorflow
. -
If you aren't still inside your Conda TensorFlow environment, enter it by typing
source activate tensorflow
-
Install TQDM by entering
pip install tqdm
-
Download and unzip this entire repo from GitHub, either interactively, or by entering
git clone https://github.com/Steven-Hewitt/Entailment-with-Tensorflow.git
-
Use
cd
to navigate into the top directory of the repo on your machine -
Launch Jupyter by entering
jupyter notebook
and, using your browser, navigate to the URL shown in the terminal output (usually http://localhost:8888/)