Sinequa said its neural search function can answer natural language questions, thanks to four deep learning models it developed with Microsoft Azure and Nvidia teams.
Enterprise search company Sinequa is adding a neural search option to its platform with the aim of giving improved accuracy and relevance to customers.
Sinequa said the new AI function is the first commercially available system to use four deep learning language models. Combined with the platform’s natural language processing and semantic search abilities, Sinequa said this will lead to improved question-answering and search relevance.
The Sinequa Search Cloud platform is designed to help employees find relevant information and insights from all enterprise sources in any language in the context of their work. The company has clients in various sectors including NASA, Pfizer, Siemens, the European Commission and Airbus Group.
The enterprise search company said its new neural search capabilities would improve relevance for customers. It added that the tech is often able to directly answer natural language questions thanks to deep neural nets that are able to better leverage meaning and context.
“Quality and breadth of information retrieval and search have long been recognised as primary drivers of productivity, but relevance is key to enabling business insights and more informed decision-making,” Sinequa president and CEO Alexandre Bilger said. “The resulting solution is the most powerful AI available for in-enterprise search.”
Sinequa said neural search models have been used by search engines such as Google and Bing. But computational requirements make them too costly and slow for most enterprises, particularly at production scale.
The search company said it optimised its models and collaborated with Microsoft Azure and Nvidia teams to create a high-performance, cost-efficient infrastructure. Sinequa added that its four deep learning models are pre-trained, configured and optimised for enterprise content.
“Sinequa is differentiating itself through its use of deep learning, by applying multiple deep learning models to provide more accurate and relevant search results,” Deep Analysis founder Alan Pelz-Sharpe said in a recent report.
Sinequa’s neural search function is currently available in beta for selected customers, with plans for general availability later this year.
10 things you need to know direct to your inbox every weekday. Sign up for the Daily Brief, Silicon Republic’s digest of essential sci-tech news.