This repository contains code to instantiate and deploy a text summarization model. The model takes a JSON input that encapsulates some text snippets and returns a text summary that represents the key information or message in the input text. The model was trained on the CNN / Daily Mail dataset. The model has a vocabulary of approximately 200k words. The model is based on the ACL 2017 paper, Get To The Point: Summarization with Pointer-Generator Networks.
The model files are hosted on IBM Cloud Object Storage. The code in this repository deploys the model as a web service in a Docker container. This repository was developed as part of the IBM Developer Model Asset Exchange and the public API is powered by IBM Cloud.
| Domain | Application | Industry | Framework | Training Data | Input Data Format |
|---|---|---|---|---|---|
| NLP | Text Summarization | General | TensorFlow | CNN / Daily Mail | Text |
-
A. See, P. J. Liu, C. D. Manning, Get To The Point: Summarization with Pointer-Generator Networks, ACL, 2017.
| Component | License | Link |
|---|---|---|
| This Repository | Apache 2.0 | LICENSE |
| Third Party Code | Apache 2.0 | LICENSE |
| Pre-Trained Model Weights | Apache 2.0 | LICENSE |
| Training Data | MIT | LICENSE |
docker: The Docker command-line interface. Follow the installation instructions for your system.- The minimum recommended resources for this model is 4GB Memory and 4 CPUs.
- If you are on x86-64/AMD64, your CPU must support AVX at the minimum.
To run the docker image, which automatically starts the model serving API, run:
$ docker run -it -p 5000:5000 quay.io/codait/max-text-summarizer
This will pull a pre-built image from the Quay.io container registry (or use an existing image if already cached locally) and run it. If you'd rather checkout and build the model locally you can follow the run locally steps below.
You can also deploy the model on Kubernetes using the latest docker image on Quay.
On your Kubernetes cluster, run the following commands:
$ kubectl apply -f https://github.com/IBM/MAX-Text-Summarizer/raw/master/max-text-summarizer.yaml
The model will be available internally at port 5000, but can also be accessed externally through the NodePort.
A more elaborate tutorial on how to deploy this MAX model to production on IBM Cloud can be found here.
Clone this repository locally. In a terminal, run the following command:
$ git clone https://github.com/IBM/MAX-Text-Summarizer.git
Change directory into the repository base folder:
$ cd MAX-Text-Summarizer
To build the docker image locally, run:
$ docker build -t max-text-summarizer .
All required model assets will be downloaded during the build process. Note that currently this docker image is CPU only (we will add support for GPU images later).
To run the docker image, which automatically starts the model serving API, run:
$ docker run -it -p 5000:5000 max-text-summarizer
The API server automatically generates an interactive Swagger documentation page. Go to http://localhost:5000 to load it. From there you can explore the API and also create test requests.
Use the model/predict endpoint to load some seed text (you can use one of the test files from the samples folder) and get predicted output from the API.
You can also test it on the command line, for example:
$ curl -d @samples/sample1.json -H "Content-Type: application/json" -XPOST http://localhost:5000/model/predictYou should see a JSON response like that below:
{
"status": "ok",
"summary_text": [
["nick gordon 's father -lrb- left and right -rrb- gave an interview about the 25-year-old fiance of bobbi kristina brown . it has been reported that gordon , 25 , has threatened suicide and has been taking xanax since . whitney houston 's daughter was found unconscious in a bathtub in january . on wednesday , access hollywood spoke exclusively to gordon 's stepfather about his son 's state of mind . "]
]
}The text summarizer preserves in the output summary text some special characters such as -lrb- (representing (), -rrb- (representing )), etc. that appear in the input sample, which is excerpted from the Daily Mail dataset.
To run the Flask API app in debug mode, edit config.py to set DEBUG = True under the application settings. You will then need to rebuild the docker image (see step 1).
To stop the Docker container, type CTRL + C in your terminal.
If you are interested in contributing to the Model Asset Exchange project or have any queries, please follow the instructions here.