New AI-based natural language feature makes complex searches in Dimensions faster and easier


LONDON, Nov. 07, 2024 (GLOBE NEWSWIRE) -- Digital Science is pleased to announce that its flagship product Dimensions, the world’s most complete database of linked research information, is launching a beta to explore the responsible use of a new AI-based Natural Language to Query technology.

Digital Science CEO Dr Daniel Hook said: “Boolean queries were a foundational approach for navigating the limitations of 1990s search technologies. However, they can be cumbersome, technically challenging, and often fail to capture the nuance of naturally phrased questions.

“With recent advancements in large language models (LLMs), we’ve developed a new, more intuitive interface for Dimensions: Natural Language to Query (NLQ), which translates user intent directly into a search-ready format.

“NLQ also overcomes a key limitation of LLM-based chat interfaces, where responses can vary each time a question is asked, making reproducibility difficult. By converting natural language input into a structured Boolean query, NLQ ensures consistency and transparency – critical elements in upholding research integrity amidst today’s demands for rigorous, reproducible results.”

The AI-assisted filtering helps users to save time while also producing accurate results. The new feature means it’s also quicker for users to preview their results, refine their search and rerun effortlessly.

The natural language search is available in open beta for Dimensions Analytics users, and applies to over 149 million publications – including journal articles, preprints, books and book chapters, and conference proceedings – indexed in Dimensions.

Why natural language?

Amye Kenall, Vice President of Product, Data & Analytics Hub, Digital Science, said: “Boolean searches are often daunting due to their complexity, and it can take time to structure them properly. With this new AI-based feature, we’re not only empowering users to improve efficiencies in their workflows but also building their confidence in running complex searches, so they can get the most out of our vast Dimensions content.

“Our research shows that even those who are confident users of Boolean searches would prefer a natural language search instead.”

The new NLQ feature is the latest in a series of Dimensions releases that represent Digital Science’s wider commitment to innovation, hand-in-hand with the responsible development of AI tools. These include Dimensions Research GPT, AI-powered summarization across multiple documents, and a Chat with PDF capability integrated within the Dimensions web experience.

Try for yourself: Dimensions users can see the beta of our Natural Language to Query search at work – or request a demo today.

Let us know if you’d like to be advised of further updates to NLQ in Dimensions.

Learn more about Dimensions' artificial intelligence initiatives.

About Dimensions
Part of Digital Science, Dimensions hosts the largest collection of interconnected global research data, re-imagining research discovery with access to grants, publications, clinical trials, patents and policy documents all in one place. dimensions.ai. Follow @DSDimensions on X and LinkedIn.

About Digital Science
Digital Science is an AI-focused technology company providing innovative solutions to complex challenges faced by researchers, universities, funders, industry and publishers. We work in partnership to advance global research for the benefit of society. Through our brands – Altmetric, Dimensions, Figshare, IFI CLAIMS Patent Services, metaphacts, OntoChem, Overleaf, ReadCube, Scismic, Symplectic, and Writefull – we believe when we solve problems together, we drive progress for all. Visit www.digital-science.com and follow @digitalsci on X or on LinkedIn.

 

Contact Data