Dutch Researcher Develops Search Engine AGNES, A 'Google For Archaeologists'

The smart search engine, called AGNES, can search for general keywords and the titles of PDFs, such as "Middle Ages" and "pottery", and is a kind of 'Google for archaeologists'.

New Delhi: Digital archives consist of an incredible quantity of archaeological reports. However, a person who wants to search for information in these archives must do so manually, which is a tedious activity. 

Archaeologist Alex Brandsen, a Postdoctoral researcher in Digital Archaeology at Leiden University, Netherlands, has used deep learning, a form of artificial intelligence, to develop a search engine that can search very precisely through archaeological information. The current search engine, called AGNES, can only search for general keywords and the titles of PDFs, such as "Middle Ages" and "pottery", according to a statement issued by Leiden University. 

"If you're looking for axes in the Middle Ages, you now have to download everything about the Middle Ages and search annually," the statement quoted the Dutch researcher as saying.

The smart search engine is a kind of 'Google for archaeologists', the statement said. 

Since the Treaty of Valletta (1992), archaeologists have been producing an enormous amount of reports. The Valletta Treaty, formally the European Convention on the Protection of the Archaeological Heritage (Revised), is a multilateral treaty of the Council of Europe which aims to protect the European archaeological heritage as a source of European collective memory and as an instrument for historical and scientific study. The 1992 treaty regulates how European archaeological heritage is handled. 

If one intends to start construction work anywhere, he or she first needs to check whether there is archaeological heritage in the ground. 

How Brandsen Developed AGNES, A Google For Archaeologists

In order to develop AGNES, Brandsen used deep learning and trained a language model to recognise words in archaeological reports, the statement said. An important factor taken into consideration was that the model should be able to recognise synonyms and distinguish between different meanings of a word. 

Brandsen said that the word bijl can refer to an artifact that one can chop things with, but it can also be a surname. He explained that if one is looking for the artifact bijl, that is all the person will find and no Mr Bijls anymore. 

The smart search engine can also be used to search for archaeological data geographically, which will retrieve information about an area specified by the user, according to the statement. 

How Accurate Is AGNES?

Brandsen tested the search engine with a colleague and said that the latter had been given a database of cremations in the early Middle Ages in the Netherlands by an expert on the period. Brandsen added that the professor has spent his whole life collecting this data, but with the search engine, the archaeologists found 30 per cent more cremations from the early Middle Ages. "So you see that even an expert doesn't know everything because there is so much data," Brandsen said.

Now, a rough version of AGNES is available online, the statement said. AGNES can carry out searches at an accuracy of about 80 per cent. 

Brandsen is going to make the search engine more accurate and expand it by also enabling searches in other languages, Leiden University said on its website.