Word Sense Disambiguation On Russe

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
Human Benchmark0.805RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark
ruT5-large-finetune0.735--
RuBERT conversational0.729--
RuBERT plain0.726--
ruRoberta-large finetune0.715--
ruBert-base finetune0.706--
Multilingual Bert0.69--
ruBert-large finetune0.682--
ruT5-base-finetune0.682--
SBERT_Large_mt_ru_finetuning0.657--
SBERT_Large0.654--
RuGPT3Large0.647--
RuGPT3Medium0.642--
MT5 Large0.633--
heuristic majority0.595Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks-
majority_class0.587Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks-
YaLM 1.0B few-shot0.587--
Golden Transformer0.587--
Baseline TF-IDF1.10.57RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark
RuGPT3Small0.57--
0 of 22 row(s) selected.
Word Sense Disambiguation On Russe | SOTA | HyperAI超神经