Szczegóły publikacji
Opis bibliograficzny
Abbreviation disambiguation in Polish press news using encoder-decoder models / Krzysztof Wróbel, Jakub Karbowski, Paweł LEWKOWICZ // W: FedCSIS 2023 [Dokument elektroniczny] : proceedings of the 18th conference on Computer Science and Intelligence Systems : September 17–20, 2023, Warsaw, Poland / eds. Maria Ganzha, [et al.]. — Wersja do Windows. — Dane tekstowe. — Warszawa : Polskie Towarzystwo Informatyczne, cop. 2023. — (Annals of Computer Science and Information Systems ; ISSN 2300-5963 ; Vol. 35). — Dod.: ART: ISBN 978-83-969601-0-8, USB: ISBN 978-83-967447-9-1. — e-ISBN: 978-83-967447-8-4. — S. 1255–1264. — Wymagania systemowe: Adobe Reader. — Tryb dostępu: https://annals-csis.org/proceedings/2023/drp/pdf/839.pdf [2023-10-06]. — Bibliogr. s. 1263, Abstr.
Autorzy (3)
- Wróbel Krzysztof
- AGHKarbowski Jakub
- AGHLewkowicz Paweł
Dane bibliometryczne
| ID BaDAP | 149290 |
|---|---|
| Data dodania do BaDAP | 2023-11-09 |
| DOI | 10.15439/2023F839 |
| Rok publikacji | 2023 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Konferencja | Conference on Computer Science and Intelligence Systems 2023 |
| Czasopismo/seria | Annals of Computer Science and Information Systems |
Abstract
The disambiguation of abbreviations and acronyms is a longstanding problem in Natural Language Processing (NLP) that has garnered significant attention from researchers. Previous approaches have employed statistical methods, semantic similarity metrics, and machine learning algorithms. Various languages and document types have been explored, with English being the most commonly studied language. Recent advances have been driven by the application of pre-trained transformer models. Standardization and addressing the challenges of multilingual and multi-document type disambiguation remain ongoing goals in the field of NLP. This paper presents an in-depth exploration of abbreviation disambiguation using state-of-the-art neural Encoder-Decoder models, specifically the ByT5 and plT5 architectures. Advanced synthetic data generation techniques are introduced and their effect on model performance is analysed. The methods are evaluated in the context of the PolEval abbreviation disambiguation competition, where the authors achieve top ranking.
