Portuguese language understanding benchmark
Paper Title:
PORTULAN ExtraGLUE Datasets and Models: Kick-starting a Benchmark for the Neural Processing of Portuguese
Published on:
8 April 2024
Primary Category:
Computation and Language
Paper Authors:
Tomás Osório,
Bernardo Leite,
Henrique Lopes Cardoso,
Luís Gomes,
João Rodrigues,
Rodrigo Santos,
António Branco
Bullets
Key Details
Machine translated GLUE/SuperGLUE benchmarks to Portuguese
Provided European and Brazilian Portuguese versions
Analyzed quality of the translated datasets
Developed baseline neural models adapted to tasks
Explore the topics in this paper
AI generated summary
Portuguese language understanding benchmark
The authors create new Portuguese language datasets by machine translating mainstream English benchmarks, to support research on neural models for Portuguese. They also provide baseline neural models adapted to these datasets.
Answers from this paper
You might also like
Galician conversational AI via adapting multilingual model
Constructing a corpus for speech synthesis
Empowering language models with translation data
Benchmark for evaluating language models on generation tasks in Indian languages
Multilingual news recommendation dataset
Automatic visualization from Chinese questions
Comments
No comments yet, be the first to start the conversation...
Sign up to comment on this paper