Summarising scientific publications from a tech-transfer perspective#
This is a simplified example illustrating how
great-ai is used in practice at ScoutinScience. The subpages show
great-ai in action by going over the lifecycle of fine-tuning and deploying a BERT-based software service.
The purpose of this example is to show you different ways in which
great-ai can assist you. The exact NLP task being solved is not central. Stemming from this and from the difficult nature of obtaining appropriate training data, the propriety dataset used for the experiments is not shared.
- You will see how the great_ai.utilities can integrate into your Data Science workflow.
- You will see how great_ai.large_file can be used to version and store your trained model.
- You will see how GreatAI should be used to prepare your model for a robust and responsible deployment.
- You will see multiple ways of customising your deployment.
One of the core features of the ScoutinScience platform is summarising research papers from a tech-transfer perspective. In short, extractive summarisation is preferred using a binary classifier trained on clients' judgement of sentence interestingness. Thus, documents are sentences, and the expected output is a binary label showing whether a sentence is "worthy" of being in the tech-transfer summary. Explaining each decision is imperative since ScoutinScience embraces applying only explainable AI (XAI) methods wherever feasible.
You are ready to start the tutorial. Feel free to return to the summary section once you're finished.
We load and analyse the data by calculating inter-rater reliability and checking the feasibility of using an AI-based approach by testing the accuracy of a trivial baseline method.
We simply fine-tune SciBERT.
We customise the GreatAI configuration, create custom caching for the model and implement an inference function that can be hardened by wrapping it in a GreatAI instance. We also extract the attention weights as a quasi-explanation.
Finally, we test the model's inference function through the GreatAI dashboard. The only thing left is to deploy the hardened service properly.
There are some other files required for deploying the notebook. For example, the config file for S3 and MongoDB or a Dockerfile for building a custom image. These are gathered and shown on a separate page.