Ruslan Mitkov

Ruslan Mitkov

Lancaster University (UK)

Keynote Title: Are rule-based approaches a thing of the past? The case of anaphora resolution

Abstract

In this talk I shall present the results of a study which evaluates and compares new variants of a popular rule-based anaphora resolution algorithm (Mitkov 1998, 2002) with the original version. We seek to establish whether configurations that benefit from Deep Learning, LLMs and eye-tracking data (always) outperform the original rule-based algorithm. The results of this study suggest that while algorithms based in Deep Learning and LLMs usually perform better than rule-based ones, this is not always the case, and we argue that rule-based approaches still have a place in today’s research.

Bio

Prof Dr Ruslan Mitkov is Professor in Computing and Communications at Lancaster University, one of the top-10 UK universities. Prior to joining Lancaster University, Prof Mitkov worked at the University of Wolverhampton where he created and led the internationally leading Research Group in Computational Linguistics, and was also Director of the Research Institute of Information and Language Processing as well as Director of the Responsible Digital Humanities Lab. Dr Mitkov has been working in Natural Language Processing (NLP), Computational Linguistics, Corpus Linguistics, Machine Translation, Translation Technology and related areas since the early 1980s.

Whereas Prof Mitkov is best known for his seminal contributions to the areas of anaphora resolution, automatic generation of multiple-choice tests and intelligent translation memory systems, his extensively cited research (more than 300 publications including 15 books, 35 journal articles and 35 book chapters) also includes but is not limited to topics such as machine translation, natural language processing for language disabilities, automatic summarisation, computer-aided language processing, corpus annotation, bilingual term extraction, automatic identification of cognates and false friends, NLP-driven corpus-based study of translation universals and text simplification. His recent research includes the employment of Deep Learning, Large Language Models and Artificial Intelligence in Natural Language Processing, linguistics and language research in general. Prof Mitkov is not only known for his original research outputs with high scientific impact, but also known for his vision and innovative applied research which seeks to enhance the work efficiency of different professions (teachers, translators and interpreters) or seeks to improve the quality of life (people with disabilities). Read More