paper-with-me

Question Answering 벤치마크

Question Answering on HotpotQA

73개 결과 · ⬇ CSV · JSON

JOINT-F1

0 0.1938 0.3875 0.5813 0.775 2018-09 2026-11 SAFSR model — 0.598 (2018-09-25) Baseline Model — 0.162 (2018-09-25) Cognitive Graph QA — 0.349 (2019-05-14) DFGN — 0.5982 (2019-05-16) QFE — 0.231 (2019-05-21) DecompRC — 0.0 (2019-06-07) MUPPET — 0.27 (2019-06-15) SemanticRetrievalMRS — 0.476 (2019-09-17) GoldEn Retriever — 0.391 (2019-10-15) KGNN — 0.247 (2019-11-06) HGN + SemanticRetrievalMRS IR — 0.599 (2019-11-09) Robustly Fine-tuned Graph-based Recurrent Retriever — 0.612 (2019-11-24) Quark + SemanticRetrievalMRS IR — 0.562 (2020-04-14) Transformer-XH-final — 0.513 (2020-05-01) BigBird-etc — 0.736 (2020-07-28) DDRQA — 0.639 (2020-09-16) Recursive Dense Retriever — 0.666 (2020-09-27) IRRR+ — 0.696 (2020-10-23) IRRR — 0.686 (2020-10-23) HopRetriever + Sp-search — 0.706 (2020-12-31) AISO — 0.72 (2021-09-14) Chain-of-Skills — 0.717 (2023-05-04) Beam Retrieval — 0.775 (2023-08-17) SAFSR model — 0.598 (2018-09-25) DFGN — 0.5982 (2019-05-16) HGN + SemanticRetrievalMRS IR — 0.599 (2019-11-09) Robustly Fine-tuned Graph-based Recurrent Retriever — 0.612 (2019-11-24) BigBird-etc — 0.736 (2020-07-28) Beam Retrieval — 0.775 (2023-08-17)
RankModel JOINT-F1ANS-EMANS-F1SUP-EMSUP-F1JOINT-EM PaperCodeYear
1 Beam Retrieval 0.7750.7270.8500.6630.9010.505 End-to-End Beam Retrieval for Multi-Hop Question Answering ShayekhBinIslam/openrag · canghongjian/beam_retriever · Alab-NII/2wikimultihop 2023
2 BigBird-etc 0.736–0.755–0.891– Big Bird: Transformers for Longer Sequences huggingface/transformers · tensorflow/models · PaddlePaddle/PaddleNLP · +11 2020
3 AISO 0.7200.6750.8050.6120.8600.449 Adaptive Information Seeking for Open-Domain Question Answering zycdev/aiso 2021
4 Chain-of-Skills 0.7170.6740.8010.6130.8530.457 Chain-of-Skills: A Configurable Model for Open-domain Question Answering mayer123/udt-qa 2023
5 TPRR 0.7080.6700.7950.5940.8430.444
6 HopRetriever + Sp-search 0.7060.6710.7990.5740.8350.432 HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions 2020
7 EBS-Large 0.7000.6620.7930.5730.8400.420
8 HopRetriever 0.6980.6710.7990.5720.8260.431
9 IRRR+ 0.6960.6630.7910.5690.8320.428 Answering Open-Domain Questions of Varying Reasoning Steps from Text beerqa/irrr 2020
10 EBS-SH 0.6890.6550.7860.5590.8310.409
11 IRRR 0.6860.6570.7820.5590.8210.421 Answering Open-Domain Questions of Varying Reasoning Steps from Text beerqa/irrr 2020
12 HopRetriever-V2 0.6780.6480.7780.5610.8180.410
13 AFSGraph-retriever 0.6700.6460.7780.5570.8120.411
14 Recursive Dense Retriever 0.6660.6230.7530.5750.8090.418 Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval facebookresearch/multihop_dense_retrieval 2020
15 Step-by-Step Retriever 0.6620.6300.7540.5460.8000.404
16 DDRQA 0.6390.6250.7590.5100.7890.360 Answering Any-hop Open-domain Questions with Iterative Document Reranking 2020
16 HopRetriever-V1 0.6390.6080.7390.5310.7930.380
18 DR model large 0.6300.6200.7530.4990.7780.354
19 Model name 0.6290.6170.7460.5000.7720.368
19 HopAns 0.6290.6170.7460.5000.7720.368
1–20 / 73 다음 → 페이지당 10 20 50 100