Berlin: Researchers have developed a new software that makes your web search easier by resolving the ambiguity of names within texts automatically.
When reading the last name “Merkel”, even people struggle to understand whether it refers to the Chancellor of Germany Angela Merkel or the famous soccer coach Max Merkel. It is a drawback for web search, too, researchers said.
Up to now, the programmes can capture character strings like “Angela Merkel”, but they do not pay attention to attributes like “German Chancellor” or “Germany’s First Lady” at all.
Even worse, after the word “Merkel” is entered, the search engines provide information about a lot of people with the same last name, researchers said.
Researchers at the Max Planck Institute for Informatics in Germany have developed a software that enables accurate disambiguation of named entities by analysing them with the help of Wikipedia.
Their software, named AIDA, establishes connections between the mentions in the text and potential persons or places.
“The more references exist between a mention and a specific person in Wikipedia, the more words of the person’s Wikipedia article can also be found in the input text, and the higher the score the mention-entity edge receives,” said Johannes Hoffart, who co-developed AIDA at the Max Planck Institute for Informatics.
“AIDA checks this score and selects the mention-entity edge with the highest score as the accurate mapping,” Hoffart said.
To demonstrate their novel technique, the researchers have implemented a search engine based on their approach.
The search engine makes it possible not only to combine the search for strings with the search for specific objects like persons and locations, but also to search on categories.
Currently the researchers use AIDA to analyse the text corpus of the German National Library to combine the search for keywords with the search for specific objects.
“With our new technique we can not only build better search engines, but also make computers understand texts almost as a human does, in an efficient way,” explained Gerhard Weikum, Scientific Director at the Max Planck Institute for Informatics.
The approach also opens new possibilities for automatically generated recommendations and the analysis of datasets, said Weikum.
“Whoever is a fan of the soccer coach Merkel will receive recommendations for his books. Those more interested in the Chancellor get referred to books dealing with her and her way of governing Germany,” Weikum said.