Skip to content

Gemma for abstractive proposition segmentation (APS)

Models Gemma APS

Gemma-APS

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.

  • Analyze content for component parts — Apply generative artificial intelligence (AI) to break down content into discrete statements for analysis or further processing.
  • Combine with larger content analysis — Use generated content segments in larger content analysis projects such as grounding, retrieval, fact-checking, evaluation of generation tasks, and duplicate content detection.

Learn more

View 2B model

View more code, notebooks, information, and discussions about the Gemma-APS 2B model on Hugging Face.

View 7B model

View more code, notebooks, information, and discussions about the Gemma-APS 7B model on Hugging Face.

Read the research

Get more insights into the research, development, and operation of the Gemma-APS model.