Abstractive proposition segmentation (APS) is an analysis technique that breaks down text information into component parts. Gemma-APS is a variant of Gemma that takes a given passage of text and attempts to segment the content into the individual facts, statements, and ideas expressed in the text, and restates them in full sentences with small changes to the original text.

This model can be used for research where there is a need to break down text content into meaningful components. Applications include generative content grounding, content retrieval, fact-checking, and evaluation of generative output, such as summarization, where it is useful to divide up individual factual data so that they can be verified independently. For more information, check out the research paper.