← Named Entity Recognition (NER)

Papers with Code · CC BY-SA 4.0

SLUE

아카이브 평가 13건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
W2V2-L-LL60K (pipeline approach, uses LM)	F1 (%) 69.6 label-F1 (%) 82.2 Text model DeBERTa-L	SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 2021-11-19	코드 1
W2V2-B-LS960 (pipeline approach, uses LM)	F1 (%) 68.0 label-F1 (%) 79.8 Text model DeBERTa-L	SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 2021-11-19	코드 1
Wav2Seq (from HuBERT-large)	F1 (%) 65.4	Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages 2022-05-02	코드 1
W2V2-L-LL60K (e2e approach, uses LM)	F1 (%) 64.8 label-F1 (%) 73.3 Text model N/A	SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 2021-11-19	코드 1
W2V2-B-LS960 (e2e approach, uses LM)	F1 (%) 63.4 label-F1 (%) 71.7 Text model N/A	SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 2021-11-19	코드 1
HuBERT-B-LS960 (e2e approach, uses LM)	F1 (%) 61.9 label-F1 (%) 70.3 Text model N/A	SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 2021-11-19	코드 1
W2V2-B-VP100K (e2e approach, uses LM)	F1 (%) 61.8 label-F1 (%) 69.8 Text model N/A	SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 2021-11-19	코드 1
W2V2-L-LL60K (pipeline approach)	F1 (%) 57.8 label-F1 (%) 78.8 Text model DeBERTa-L	SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 2021-11-19	코드 1
W2V2-L-LL60K (e2e approach)	F1 (%) 50.9 label-F1 (%) 64.7 Text model -	SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 2021-11-19	코드 1
W2V2-B-LS960 (e2e approach)	F1 (%) 50.2 label-F1 (%) 64.0 Text model -	SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 2021-11-19	코드 1
HuBERT-B-LS960 (e2e approach)	F1 (%) 49.8 label-F1 (%) 62.9 Text model -	SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 2021-11-19	코드 1
W2V2-B-LS960 (pipeline approach)	F1 (%) 49.5 label-F1 (%) 74.2 Text model DeBERTa-L	SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 2021-11-19	코드 1
W2V2-B-VP100K (e2e approach)	F1 (%) 47.9 label-F1 (%) 60.8 Text model -	SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech 2021-11-19	코드 1