IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10426924" target="_blank" >RIV/00216208:11320/20:10426924 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.aclweb.org/anthology/2020.coling-main.66" target="_blank" >https://www.aclweb.org/anthology/2020.coling-main.66</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP

Popis výsledku v původním jazyce

Although the Indonesian language is spoken by almost 200 million people and the 10th most spoken language in the world, it is under-represented in NLP research. Previous work on Indonesian has been hampered by a lack of annotated datasets, a sparsity of language resources, and a lack of resource standardization. In this work, we release the IndoLEM dataset comprising seven tasks for the Indonesian language, spanning morpho-syntax, semantics, and discourse. We additionally release IndoBERT, a new pre-trained language model for Indonesian, and evaluate it over IndoLEM, in addition to benchmarking it against existing resources. Our experiments show that IndoBERT achieves state-of-the-art performance over most of the tasks in IndoLEM.

Název v anglickém jazyce

IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP

Popis výsledku anglicky

Although the Indonesian language is spoken by almost 200 million people and the 10th most spoken language in the world, it is under-represented in NLP research. Previous work on Indonesian has been hampered by a lack of annotated datasets, a sparsity of language resources, and a lack of resource standardization. In this work, we release the IndoLEM dataset comprising seven tasks for the Indonesian language, spanning morpho-syntax, semantics, and discourse. We additionally release IndoBERT, a new pre-trained language model for Indonesian, and evaluate it over IndoLEM, in addition to benchmarking it against existing resources. Our experiments show that IndoBERT achieves state-of-the-art performance over most of the tasks in IndoLEM.

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

2020

Kód důvěrnosti údajů

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