- Organised by : Ermia Anvari
- Deadline : May 29, 2020
- Challenge Link: https://www.kaggle.com/c/the-allen-ai-science-challenge
The Allen Institute for Artificial Intelligence (AI2) is working to improve humanity through fundamental advances in artificial intelligence. One critical but challenging problem in AI is to demonstrate the ability to consistently understand and correctly answer general questions about the world. The Aristo project at AI2 is focused on building such a system. One way Aristo "learns" is by extracting facts from various sources and processing them into a structured knowledge base. When taking an exam, questions are parsed and processed along with any accompanying diagrams to determine a strategy for answering. Aristo then uses entailment, statistical analysis, and inference methods to select a final answer. While Aristo's abilities have improved significantly in the last two years, it still doesn't have perfect, reliable methods of gathering knowledge, understanding questions, or reasoning through answers. Using a dataset of multiple choice question and answers from a standardized 8th grade science exam, AI2 is challenging you to create a model that gets to the head of the class.
Repository link | Description | Contact | Repository image name |
---|---|---|---|
https://bitbucket.org/bonseyes/wp3-pipeline-mnist | The training data consists of 2,500 multiple choice questions from a typical US 8th grade science curriculum. Each question has four possible answers, of which exactly one is correct. Note that the questions in these datasets are private intellectual p | ermia.anvari@synyo.com | yuliyanm/bonseyes:inference_image_mbc_v1 |
https://bitbucket.org/bonseyes/wp3-pipeline-mnist | test | anvari182@gmail.com | yuliyanm/bonseyes:inference_image_mbc_v1 |
http://bonseyes.synyocreative.com/challenge | Solution with 95% accuracy | thomas.paulin@synyo.com | my_solution |
test | anvari182@gmail.com |