Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic Roles

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427082" target="_blank" >RIV/00216208:11320/19:10427082 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.aclweb.org/anthology/W19-0417" target="_blank" >https://www.aclweb.org/anthology/W19-0417</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic Roles

Popis výsledku v původním jazyce

We describe a transfer method based on annotation projection to develop a dependency-based semantic role labeling system for languages for which no supervised linguistic information other than parallel data is available. Unlike previous work that presumes the availability of supervised features such as lemmas, part-of-speech tags, and dependency parse trees, we only make use of word and character features. Our deep model considers using character-based representations as well as unsupervised stem embeddings to alleviate the need for supervised features. Our experiments outperform a state-of-the-art method that uses supervised lexico-syntactic features on 6 out of 7 languages in the Universal Proposition Bank.

Název v anglickém jazyce

Cross-Lingual Transfer of Semantic Roles: From Raw Text to Semantic Roles

Popis výsledku anglicky

We describe a transfer method based on annotation projection to develop a dependency-based semantic role labeling system for languages for which no supervised linguistic information other than parallel data is available. Unlike previous work that presumes the availability of supervised features such as lemmas, part-of-speech tags, and dependency parse trees, we only make use of word and character features. Our deep model considers using character-based representations as well as unsupervised stem embeddings to alleviate the need for supervised features. Our experiments outperform a state-of-the-art method that uses supervised lexico-syntactic features on 6 out of 7 languages in the Universal Proposition Bank.

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

2019

Kód důvěrnosti údajů

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