BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Liverpool Computer Science Seminar System//v2//EN
BEGIN:VEVENT
DTSTAMP:20260920T212508Z
UID:Seminar-dept-1062@lxserverM.csc.liv.ac.uk
ORGANIZER:CN=Lutz Oettershagen:MAILTO:Lutz.Oettershagen@liverpool.ac.uk
DTSTART:20231017T130000
DTEND:20231017T140000
SUMMARY:School Seminar Series
DESCRIPTION:Prof. Mamoru Komachi: Cross-lingual transfer learning with multilingual masked language models\n\nThis talk introduces the innovative realm of Multilingual Masked Language Models (MMLMs) as a crucial tool in the pursuit of effective cross-lingual transfer learning. The discussion aims to elucidate the underlying architecture, functionality, and practical applications of MMLMs in advancing NLP’s multilingual capabilities. \n\n\n\nIn the first part, I talk about key elements such as the transformer-based architecture, the masking mechanism integral to their operation, and the training process for transfer learning. These components collectively work in tandem to facilitate the model's ability to both understand and generate text in a multitude of languages.\n\n\n\nIn the second part, I argue how we can enhance few-shot learning, which uses only a small amount of training data for fine-tuning a model, by carefully selecting candidates for MMLMs. The main idea is to select hard examples for annotation to improve the model's performance. I show that zero-shot learning can be used to detect hard examples for cross-lingual transfer. \n\n\n\nThis talk aims to offer attendees a coherent and comprehensive understanding of MMLMs and their practical applications, including grammatical error correction and named entity recognition.\n\nhttps://www.csc.liv.ac.uk/research/seminars/abstract.php?id=1062
LOCATION:Ashton Lecture Theatre
END:VEVENT
END:VCALENDAR