Question Answering On Hotpotqa

ANS-EM

ANS-F1

JOINT-EM

JOINT-F1

SUP-EM

SUP-F1

评测结果

各个模型在此基准测试上的表现结果

							Paper Title	Repository
Beam Retrieval	0.727	0.850	0.505	0.775	0.663	0.901	End-to-End Beam Retrieval for Multi-Hop Question Answering
BigBird-etc	-	0.755	-	0.736	-	0.891	Big Bird: Transformers for Longer Sequences
AISO	0.675	0.805	0.449	0.720	0.612	0.860	Adaptive Information Seeking for Open-Domain Question Answering
Chain-of-Skills	0.674	0.801	0.457	0.717	0.613	0.853	Chain-of-Skills: A Configurable Model for Open-domain Question Answering
TPRR	0.670	0.795	0.444	0.708	0.594	0.843	-	-
HopRetriever + Sp-search	0.671	0.799	0.432	0.706	0.574	0.835	HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions	-
EBS-Large	0.662	0.793	0.420	0.700	0.573	0.840	-	-
HopRetriever	0.671	0.799	0.431	0.698	0.572	0.826	-	-
IRRR+	0.663	0.791	0.428	0.696	0.569	0.832	Answering Open-Domain Questions of Varying Reasoning Steps from Text
EBS-SH	0.655	0.786	0.409	0.689	0.559	0.831	-	-
IRRR	0.657	0.782	0.421	0.686	0.559	0.821	Answering Open-Domain Questions of Varying Reasoning Steps from Text
HopRetriever-V2	0.648	0.778	0.410	0.678	0.561	0.818	-	-
AFSGraph-retriever	0.646	0.778	0.411	0.670	0.557	0.812	-	-
Recursive Dense Retriever	0.623	0.753	0.418	0.666	0.575	0.809	Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval
Step-by-Step Retriever	0.630	0.754	0.404	0.662	0.546	0.800	-	-
HopRetriever-V1	0.608	0.739	0.380	0.639	0.531	0.793	-	-
DDRQA	0.625	0.759	0.360	0.639	0.510	0.789	Answering Any-hop Open-domain Questions with Iterative Document Reranking	-
DR model large	0.620	0.753	0.354	0.630	0.499	0.778	-	-
HopAns	0.617	0.746	0.368	0.629	0.500	0.772	-	-
Model name	0.617	0.746	0.368	0.629	0.500	0.772	-	-

0 of 72 row(s) selected.