We stand with Ukraine

At the First “AI vs. Human” Crossword Puzzle Challenge in French, English and Italian, Artificial Intelligence Wins

20 February 2023

The French version of WebCrow, the crossword puzzle solving software developed by the University of Siena in collaboration with expert.ai and, for this occasion with the valuable contribution of the 3IA Côte d’Azur institute and the INRIA Center, made its debut at the World Artificial Intelligence Festival in Cannes (WAICF).

WebCrow at WAICF 2023

The team from the University of Siena and expert.ai that created the AI WebCrow software with team leader Professor Marco Gori (right) of the Department of Information Engineering and Mathematical Sciences, University of Siena.

In addition to competing in Italian and (American) English, for the first time, WebCrow competed on French crossword puzzles, and AI was the winner in all of the competitions across the three languages.

How WebCrow works

WebCrow simultaneously leverages a very powerful web search module that can select correct answers based on crossword puzzle definitions and the power of artificial intelligence from expert.ai, a leading company in natural language understanding and processing technologies. Expert.ai, which has been active in the AI market for more than two decades with hundreds of successful implementations for business and government, helps organizations improve any activity or process based on language understanding and processing, making the most of information, extracting the maximum value from business data and thus accelerating digital transformation, intelligent process automation and any strategic decision making.

Understanding, Knowledge Graph, Reasoning

WebCrow 2.0 has been empowered with typical human skills to simulate human-like processes for reading, understanding and reasoning. This allows the software to identify the meaning of words based on definitions and other clues in crossword puzzles. It accomplishes this by:

Understanding: Utilizing several logical and language analysis steps focused on understanding clues.

Knowledge: Finding the correct meaning requires inferences and reasoning that makes use of knowledge in various sources. Expert.ai’s knowledge graph enables this with the market’s richest conceptual database for understanding language.

Reasoning: A combination of advanced AI, NLU with NLP, machine learning and constraint satisfaction technologies identify possible words, evaluate them and enter the answers in the puzzle grid.

Read more about the WebCrow project and WebCrow’s presence at the World AI Cannes Festival: https://webcrow-arena.diism.unisi.it/.