paper-with-me

GLUE

General Language Understanding Evaluation benchmark

홈페이지 · 논문 3,197편

General Language Understanding Evaluation (GLUE) benchmark is a collection of nine natural language understanding tasks, including single-sentence tasks CoLA and SST-2, similarity and paraphrasing tasks MRPC, STS-B and QQP, and natural language inference tasks MNLI, QNLI, RTE and WNLI. Source: Align, Mask and Select: A Simple Method for Incorporating Commonsense Knowledge into Language Representation Models Image Source: https://gluebenchmark.com/

Texts English

벤치마크

Natural Language Inference on RTE 결과 90개

Semantic Textual Similarity on MRPC 결과 45개

Linguistic Acceptability on CoLA 결과 43개

Natural Language Inference on QNLI 결과 43개

Natural Language Inference on WNLI 결과 23개

Data-free Knowledge Distillation on QNLI 결과 8개

Classification on SST-2 결과 6개

Text Classification on SST-2 결과 6개

Text Classification on GLUE SST2 결과 4개

Classification on RTE 결과 2개

Few-Shot Learning on GLUE QQP 결과 2개

Few-Shot Learning on MRPC 결과 2개

Model Compression on QNLI 결과 2개

Natural Language Understanding on GLUE 결과 2개

Text Classification on GLUE COLA 결과 2개

Text Classification on GLUE MRPC 결과 2개

Text Classification on GLUE RTE 결과 2개

Text Classification on GLUE STSB 결과 2개

Natural Language Inference on MRPC 결과 1개

Stochastic Optimization on CoLA 결과 1개