acm-header
Sign In

Communications of the ACM

ACM Careers

Automatic Information System Extracts Scientific Articles on COVID-19


Eneko Agirre and Xabier Saralegi

Eneko Agirre and Xabier Saralegi helped construct a system that extracts answers about questions on COVID from scientific literature.

Credit: UPV / EHU

Researchers from the University of the Basque Country, the National Distance Education University, and Elhuyar have created the VIGICOVID system that addresses the need to search for answers in the avalanche of information generated by research conducted across the world relating to the COVID-19 pandemic. By means of artificial intelligence, the system displays the answers found in a set of scientific articles in an orderly fashion, and uses natural language questions and answers.

"The information search paradigm is changing thanks to artificial intelligence," says Eneko Agirre, director of the HiTZ Centre for Language Technology at the University of the Basque Country.

"We found that a recall based document retrieval that leaves to a neural answer extraction module the scanning of the whole documents to find the best answer is a better strategy than relying in a precise passage retrieval before extracting the answer span," the researchers says in "Information Retrieval and Question Answering: A Case Study on COVID-19 Scientific Literature," published in Knowledge-Based Systems.

The research shows that the proposed technology works, and that the system provides good results, Agirre says.

From University of the Basque Country
View Full Article


 

No entries found