Question Answering on WikiQA

Metric: MRR (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

#	Model↕	MRR▼	Extra Data	Paper	Date↕	Code
1	TANDA-DeBERTa-V3-Large + ALL	0.939	Yes	Structural Self-Supervised Objectives for Transf...	2023-09-15	Code
2	TANDA-RoBERTa (ASNQ, WikiQA)	0.933	Yes	TANDA: Transfer and Adapt Pre-Trained Transforme...	2019-11-11	Code
3	DeBERTa-V3-Large + ALL	0.92	No	Pre-training Transformer Models with Sentence-Le...	2022-05-20	-
4	DeBERTa-Large + SSP	0.914	No	Pre-training Transformer Models with Sentence-Le...	2022-05-20	-
5	RLAS-BIABC	0.908	Yes	RLAS-BIABC: A Reinforcement Learning-Based Answe...	2023-01-07	-
6	RoBERTa-Base Joint MSPP	0.9	No	Paragraph-based Transformer Pre-training for Mul...	2022-05-02	Code
7	RoBERTa-Base + SSP	0.899	No	Pre-training Transformer Models with Sentence-Le...	2022-05-20	-
8	Comp-Clip + LM + LC	0.784	No	A Compare-Aggregate Model with Latent Clustering...	2019-05-30	-
9	RE2	0.7618	No	Simple and Effective Text Matching with Richer A...	2019-08-01	Code
10	HyperQA	0.727	No	Hyperbolic Representation Learning for Fast and ...	2017-07-25	Code
11	Key-Value Memory Network	0.7265	No	Key-Value Memory Networks for Directly Reading D...	2016-06-09	Code
12	PWIM	0.7234	No	-	-	-
13	LDC	0.7226	No	Sentence Similarity Learning by Lexical Decompos...	2016-02-23	Code
14	PairwiseRank + Multi-Perspective CNN	0.718	No	Noise Contrastive Estimation and Negative Sampli...	2018-09-06	-
15	Attentive LSTM	0.7069	No	Neural Variational Inference for Text Processing	2015-11-19	Code
16	MMA-NSE attention	0.6993	No	Neural Semantic Encoders	2016-07-14	Code
17	LSTM (lexical overlap + dist output)	0.6988	No	Neural Variational Inference for Text Processing	2015-11-19	Code
18	AP-CNN	0.6957	No	Attentive Pooling Networks	2016-02-11	Code
19	SWEM-concat	0.6908	No	Baseline Needs More Love: On Simple Word-Embeddi...	2018-05-24	Code
20	LSTM	0.6747	No	Neural Variational Inference for Text Processing	2015-11-19	Code
21	Bigram-CNN (lexical overlap + dist output)	0.6652	No	Deep Learning for Answer Sentence Selection	2014-12-04	Code
22	CNN-Cnt	0.6652	No	-	-	-
23	Bigram-CNN	0.6281	No	Deep Learning for Answer Sentence Selection	2014-12-04	Code
24	Paragraph vector (lexical overlap + dist output)	0.6058	No	Distributed Representations of Sentences and Doc...	2014-05-16	Code
25	Paragraph vector	0.516	No	Distributed Representations of Sentences and Doc...	2014-05-16	Code