AI Seminar Series 2020: Yixing Luan on Word Sense Disambiguation

The Artificial Intelligence (AI) Seminar is a weekly meeting at the University of Alberta where researchers interested in AI can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems, are explored.

On July 31, 2020, Amii researcher (under the supervision of Amii Fellow and UAlberta Professor of Computing Science Greg Kondrak) Yixing Luan presented Leveraging Translations for Word Sense Disambiguation.

The objective of word sense disambiguation (WSD) is to identify the correct sense of a content word in context and is one of the core tasks in natural language processing (NLP). Existing WSD systems rarely consider multilingual information (e.g. translations), and no effective method has yet been proposed for improving WSD with machine translation. 

In this talk, Yixing proposes methods of leveraging translations from multiple languages as a constraint to boost the accuracy of existing WSD systems, resulting in a novel knowledge-based word alignment algorithm that demonstrates state-of-the-art results in both English and multilingual WSD.

Watch the full presentation below:

Learn how Amii advances world-leading artificial intelligence and machine learning research: visit our Research page.