Yes. If you are satisfied with an average B grade, and are willing to part with your lunch money to train a ML model (rather than on smash avo on toast).
Multiple choice questions. On face value, might seem like a purely academic use case with no real world applications. But hear me out - Answering questions which require reasoning, and picking the best solution out of possible outcomes, based on prior knowledge, is not a trivial problem to solve. Natural Language ML models that solve problems in this domain can be applied to other use cases such as:
Health: Best treatment based on a patient’s diagnosis;
Legal: Predict the outcome of a legal case based on multiple scenarios;
Marketing/Advertising: Custom advertising based on a customer's profile;
Customer service: Next best action based on a conversation with a customer, or chatbots/assistants;
Creative: Movie script generation - Select the best movie ending scene.
We carried out a cursory exercise on a simple multiple choice questions dataset, and built a ML model that was able to pick the correct answer ~73% of the time, with just 5 minutes of ML model training.
The objectives is to train a Natural Language ML model to answer multiple choice questions from the OpenBookQA dataset
OpenBookQA is a question-answering dataset modeled after open book exams for assessing human understanding of a subject. It consists of 5,957 multiple-choice elementary-level science questions (4,957 train, 500 dev, 500 test), which probe the understanding of a small “book” of 1,326 core science facts and the application of these facts to novel situations.
For the test dataset of 500 MCQs, the model picked the correct answer ~73% (366/500) of the time, with just 5 minutes of training. Results and predictions can be found here.
The NoamAi platform is a fully automated NLP system, embodying the principles of DevOps and CI/CD (MLOps) in machine learning (ML) and AI. It simplifies and automates the end to end ML model build process (data preparation -> model training -> model deployment) by ways of standardisation, consistency, speed and scale. All users need to do is to provide the data and define the problem.
The platform has the ability to build models for the following use cases:
Classification - Classify sentences or text narratives (i.e. sentiment analysis)
Comprehension - Answer questions based on paragraphs of text
Summarisation - Summarising of text
Named entity recognition - Text information extraction into predefined categories such as person names, organizations, locations, medical codes, time expressions, quantities, monetary values, percentages
Market leaders have recognised that:
Machine learning and AI have demonstrated benefits and value in an organisation
Standardization & automation of ML drive speed, scale and efficiencies
Teams become productive in their day jobs
Giving them the capacity to innovate
Allowing for breakthroughs and discoveries
Which improves and matures Machine Learning in an organisation
And increases return of investment