Natural Language Processing in Cultural Heritage Domains: Integrating Pretrained Language Models with Rule-based Systems for Historical Japanese Corpora

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AL9WAGMI3" target="_blank" >RIV/00216208:11320/23:L9WAGMI3 - isvavai.cz</a>

Výsledek na webu

<a href="https://search.proquest.com/openview/8496c415f0499320865f99e2cadcf33a/1?pq-origsite=gscholar&cbl=18750&diss=y" target="_blank" >https://search.proquest.com/openview/8496c415f0499320865f99e2cadcf33a/1?pq-origsite=gscholar&cbl=18750&diss=y</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Natural Language Processing in Cultural Heritage Domains: Integrating Pretrained Language Models with Rule-based Systems for Historical Japanese Corpora

Popis výsledku v původním jazyce

"Annotation of unlabeled textual corpora with linguistic features is a fundamen-ntal technology in the computational study of cultural heritage materials and digitalnhumanities (DH). Recent advances in natural language processing (NLP) have lever-naged pretrained language models (LMs), e.g., BERT, RoBERTa, ELECTRA, to offernsimultaneous tokenization, tagging, and dependency parsing of unlabeled text, us-ning popular annotation schemes like Universal Dependencies (UD)."

Název v anglickém jazyce

Natural Language Processing in Cultural Heritage Domains: Integrating Pretrained Language Models with Rule-based Systems for Historical Japanese Corpora

Popis výsledku anglicky

"Annotation of unlabeled textual corpora with linguistic features is a fundamen-ntal technology in the computational study of cultural heritage materials and digitalnhumanities (DH). Recent advances in natural language processing (NLP) have lever-naged pretrained language models (LMs), e.g., BERT, RoBERTa, ELECTRA, to offernsimultaneous tokenization, tagging, and dependency parsing of unlabeled text, us-ning popular annotation schemes like Universal Dependencies (UD)."

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů