Mitigating the knowledge acquisition bottleneck for Hungarian word sense disambiguation using multilingual transformers

A major hurdle in training all-words word sense disambiguation (WSD) systems for new domains and/or languages is the limited availability of sense annotated training corpora and that their construction is an extremely costly and labor-intensive process. In this paper, we investigate the utilization...

Full description

Saved in:
Bibliographic Details
Main Author: Berend Gábor
Corporate Author: Magyar számítógépes nyelvészeti konferencia (17.) (2021) (Szeged)
Format: Book part
Published: 2021
Series:Magyar Számítógépes Nyelvészeti Konferencia 17
Kulcsszavak:Nyelvészet - számítógép alkalmazása
Subjects:
Online Access:http://acta.bibl.u-szeged.hu/73359
Description
Summary:A major hurdle in training all-words word sense disambiguation (WSD) systems for new domains and/or languages is the limited availability of sense annotated training corpora and that their construction is an extremely costly and labor-intensive process. In this paper, we investigate the utilization of multilingual transformer-based language models for performing cross-lingual WSD in the zero-shot setting. Our empirical results suggest that by relying on the intriguing multilingual abilities of pre-trained language models, we can infer reliable sense labels to Hungarian textual utterances in the all-word WSD setting by purely relying on sense-annotated training data in English.
Physical Description:77-89
ISBN:978-963-306-781-9