Multilingual Dependency Parsing from Universal Dependencies to Sesame Street
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10426971" target="_blank" >RIV/00216208:11320/20:10426971 - isvavai.cz</a>
Výsledek na webu
<a href="https://www.springer.com/series/558" target="_blank" >https://www.springer.com/series/558</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Multilingual Dependency Parsing from Universal Dependencies to Sesame Street
Popis výsledku v původním jazyce
Research on dependency parsing has always had a strong multilingual orientation, but the lack of standardized annotations for a long time made it difficult both to meaningfully compare results across languages and to develop truly multilingual systems. The Universal Dependencies project has during the last five years tried to overcome this obstacle by developing cross-linguistically consistent morphosyntactic annotation for many languages. During the same period, dependency parsing (like the rest of NLP) has been transformed by the adoption of continuous vector representations and neural network techniques. In this paper, I will introduce the framework and resources of Universal Dependencies, and discuss advances in dependency parsing enabled by these resources in combination with deep learning techniques, ranging from traditional word and character embeddings to deep contextualized word representations like ELMo and BERT.
Název v anglickém jazyce
Multilingual Dependency Parsing from Universal Dependencies to Sesame Street
Popis výsledku anglicky
Research on dependency parsing has always had a strong multilingual orientation, but the lack of standardized annotations for a long time made it difficult both to meaningfully compare results across languages and to develop truly multilingual systems. The Universal Dependencies project has during the last five years tried to overcome this obstacle by developing cross-linguistically consistent morphosyntactic annotation for many languages. During the same period, dependency parsing (like the rest of NLP) has been transformed by the adoption of continuous vector representations and neural network techniques. In this paper, I will introduce the framework and resources of Universal Dependencies, and discuss advances in dependency parsing enabled by these resources in combination with deep learning techniques, ranging from traditional word and character embeddings to deep contextualized word representations like ELMo and BERT.
Klasifikace
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)
Návaznosti výsledku
Projekt
—
Návaznosti
—
Ostatní
Rok uplatnění
2020
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů