What if search worked differently? What if you could type a query in your own language — cambio climático, énergies renouvelables, 再生可能エネルギー — and find relevant results in English, French, Spanish, Japanese, or beyond, without ever translating a word? In June 2025, COAR launched a project to investigate the potential of semantic multilingual searching in the context of scholarly literature and develop a proposed conceptual model that could apply this technology in repositories and their full text aggregations.

Multilingualism is a critical characteristic of a healthy, inclusive, and diverse research communications landscape. Publishing in a local language ensures that the public in different countries has access to the research they fund, and also levels the playing field for researchers who speak different languages. The Helsinki Initiative on Multilingualism in Scholarly Communication asserts that the disqualification of local or national languages in academic publishing is the most important – and often forgotten – factor that prevents societies from using and taking advantage of the research done where they live.

Every day, researchers around the world produce knowledge in hundreds of languages — Spanish in Argentina, Portuguese in Brazil, Arabic in Egypt, Japanese in Japan, Swahili in Kenya. This linguistic diversity is not a side note; it is the lifeblood of global scholarship. And yet, when we go looking for that knowledge, the tools at our disposal behave as if only a handful of languages truly matter. This multilingualism presents a particular challenge for the discovery of research outputs in repositories. Although researchers and other information seekers may only be able to read in one or two languages, they want to know about all the relevant research in their area, regardless of the language in which it is published. Yet, discovery systems such as Google Scholar and other scholarly indexes tend to provide access only to the content available in the language of the user.

Collectively, repositories hold content representing hundreds of different languages. This multilingualism is an extremely valuable attribute of the global repository network. To that end, COAR is developing and promoting practices and models that improve and advance multilingualism across the repository network.

Can Semantic Multilingual Search Improve the Accessibility of Research Outputs Across Languages? A COAR Proposal In November 2025, COAR published a paper presenting a promising new approach for multilingual discovery, called multilingual semantic search. Instead of proposing a fixed technical design, the document invites the community to consider how semantic multilingual search could evolve within the broader ecosystem of scholarly communication. It reflects on early experiences, shared principles, and collective responsibilities to ensure that this new generation of discovery tools advances openness, equity, and linguistic diversity. Read the paper and give us your feedback.

COAR Task Force on Supporting Multilingualism and Non-English Content in Repositories

• 
  Can Semantic Multilingual Search Improve the Accessibility of Research Outputs Across Languages? A COAR Proposal
• 
  Breaking language barriers in science through semantic multilingual search
• 
  New version of the Resource Type Vocabulary now available
• 
  Managing multilingual and non-English language content in repositories
• 
  COAR community consultation on managing non-English and multilingual content in repositories