Indian-origin researcher at the University of Liverpool has developed a set of algorithms to teach computers to process and understand human languages, making them more interactive and taking the task of translation beyond the confines of human skill alone.
Whilst mastering technical process is easy for computers, learning and understanding human language is not achieved by programmers of computers so far. For humans, it was easier to understand language through a variety of ways such as looking up it in a dictionary, or by associating it with words in the same sentence in a meaningful way.
The new algorithms will enable a computer to act in much the same way as a human would when encountered with an unknown word. When the computer encounters a word it doesn’t recognise or understand, the algorithms mean it will look up the word in a dictionary (such as the WordNet), and tries to guess what other words should appear with this unknown word in the text.
It gives the computer a semantic representation for a word that is both consistent with the dictionary as well as with the context in the text. To achieve that the algorithm has provided the computer with an accurate representation of a word, it compares similarity scores produced using the word representations learnt by the computer algorithm against human rated similarities.
Liverpool computer scientist, Dr Danushka Bollegala, said: “Learning accurate word representations is the first step towards teaching languages to computers… If we can represent the meaning for a word in a way a computer could understand, then the computer will be able to read texts on behalf of humans and perform potentially useful tasks such as translating a text written in a foreign language, summarising a lengthy article, or find similar other documents from the Internet.”
Bollegala says there is immense possibility that will be brought about when such accurate semantic representations are used in various language processing tasks by the computers. The research was presented at the Association for Advancement of Artificial Intelligence Conference (AAAI-2016) held in Arizona, USA.
Bollegala specializes in Artificial Intelligence, Computational Linguistic and Web Mining. He has worked on various topics related to measuring semantic and relational similarity from Web data, domain adaptation, sentiment analysis, social media, personal name disambiguation, name alias extraction, and information ordering in multi-document text summarization.