Topical is a small language model specialized for topic extraction. Given a document Pleias-Topic-Deduction will return a main topic that can be used for further downstream tasks (annotation, embedding indexation)
Like other model from PleIAs Bad Data Toolbox, Topical has been volontarily trained on 70,000 documents extracted from Common Corpus with a various range of digitization artifact.
Topical is a lightweight model (70 million parameters) tha can be especially used for classification at scale on a large corpus.