Probing Multilingual Sentence Representations With X-Probe

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427071" target="_blank" >RIV/00216208:11320/19:10427071 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.aclweb.org/anthology/W19-4318" target="_blank" >https://www.aclweb.org/anthology/W19-4318</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Probing Multilingual Sentence Representations With X-Probe

Popis výsledku v původním jazyce

This paper extends the task of probing sentence representations for linguistic insight in a multilingual domain. In doing so, we make two contributions: first, we provide datasets for multilingual probing, derived from Wikipedia, in five languages, viz. English, French, German, Spanish and Russian. Second, we evaluate six sentence encoders for each language, each trained by mapping sentence representations to English sentence representations, using sentences in a parallel corpus. We discover that cross-lingually mapped representations are often better at retaining certain linguistic information than representations derived from English encoders trained on natural language inference (NLI) as a downstream task.

Název v anglickém jazyce

Probing Multilingual Sentence Representations With X-Probe

Popis výsledku anglicky

This paper extends the task of probing sentence representations for linguistic insight in a multilingual domain. In doing so, we make two contributions: first, we provide datasets for multilingual probing, derived from Wikipedia, in five languages, viz. English, French, German, Spanish and Russian. Second, we evaluate six sentence encoders for each language, each trained by mapping sentence representations to English sentence representations, using sentences in a parallel corpus. We discover that cross-lingually mapped representations are often better at retaining certain linguistic information than representations derived from English encoders trained on natural language inference (NLI) as a downstream task.

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