Ontologies have a fundamental role in leveraging the power of large language models — for the benefit of pharma and the public at large. For people and machines to use the same language to talk about scientific things, unstructured content must be transformed into ordered machine-readable data for scientific discovery in the life sciences. This involves working with expert scientific curators to encode their expertise into software.
Ontologies are a codification of scientific facts as we understand them and offer a methodology to leverage the power of new AI technologies such as large language models (LLMs). While LLMs can bring in their natural language and summarizing skills, ontologies can provide the backbone of scientific knowledge that the LLM can use, as well as make the output explainable and reproducible.
On a fundamental level, ontologies provide an agreed-upon and structured understanding of scientific language. Ontologies not only help scientists extract knowledge from scientific literature but address other barriers such as dealing with all text ambiguities. But ontologies are only valuable if they’re available to everyone; in other words, ontologies must be open to be useful. AI technologies are super powerful, but the output must still be verified as truth. Ontologies represent the truth as agreed upon by humans: that something is this type of thing, and it relates to these other types of things. So, if we can feed that into our AI, we get the best of both worlds.
Moreover, new technologies allow asking scientific questions in natural language. In turn, the LLMs will translate that into something structured and be able to request that across all these different data sources. And then they come back with something scientists can understand, complete with references. Thus, it’s no longer a black box but a kind of explainable AI solution.
Click here to read the original article published by Elsevier.
Please give your feedback on this article or share a similar story for publishing by clicking here.
