The current Kaggle challenge (typically for machine learning … )
Can you extract meaning from a large, text-based dataset derived from inventions? Here’s your chance to do so.
In this competition, you will train your models on a novel semantic similarity dataset to extract relevant information by matching key phrases in patent documents. For example, if one invention claims “television set” and a prior publication describes “TV set”, a model would ideally recognize these are the same. The best solutions will extend beyond paraphrase identification and use the technical domain context to assist a patent attorney or examiner in retrieving relevant documents.
June 13, 2022
Join This Competition
Help the patent community connect the dots between millions of patent documents with your phrase-matching model.
Kaggle Data Scientist