ML Research Wiki / Benchmarks / Question Answering / WikiQA

WikiQA

Question Answering Benchmark

Performance Over Time

📊 Showing 23 results | 📏 Metric: MAP

Top Performing Models

Rank	Model	Paper	MAP	Date	Code
1	TANDA-DeBERTa-V3-Large + ALL 📚	Structural Self-Supervised Objectives for Transformers	0.93	2023-09-15	📦 lucadiliello/transformers-framework
2	RLAS-BIABC 📚	RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm	0.92	2023-01-07	-
3	TANDA-RoBERTa (ASNQ, WikiQA) 📚	TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection	0.92	2019-11-11	📦 alexa/wqa_tanda 📦 samrelins/tanda_search_qa_tool
4	DeBERTa-V3-Large + ALL	Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection	0.91	2022-05-20	-
5	DeBERTa-Large + SSP	Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection	0.90	2022-05-20	-
6	RoBERTa-Base Joint MSPP	Paragraph-based Transformer Pre-training for Multi-Sentence Inference	0.89	2022-05-02	📦 amazon-research/wqa-multi-sentence-inference
7	RoBERTa-Base + SSP	Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection	0.89	2022-05-20	-
8	Comp-Clip + LM + LC	A Compare-Aggregate Model with Latent Clustering for Answer Selection	0.76	2019-05-30	-
9	RE2	Simple and Effective Text Matching with Richer Alignment Features	0.75	2019-08-01	📦 alibaba-edu/simple-effective-text-matching 📦 hitvoice/RE2 📦 alibaba-edu/simple-effective-text-matching-pytorch
10	HyperQA	Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering	0.71	2017-07-25	📦 vanzytay/WSDM2018_HyperQA

All Papers (23)

Structural Self-Supervised Objectives for Transformers

2023

TANDA-DeBERTa-V3-Large + ALL

lucadiliello/transformers-framework

RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm

2023

RLAS-BIABC

TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection

2019

TANDA-RoBERTa (ASNQ, WikiQA)

alexa/wqa_tanda samrelins/tanda_search_qa_tool

Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection

2022

DeBERTa-V3-Large + ALL

Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection

2022

DeBERTa-Large + SSP

Paragraph-based Transformer Pre-training for Multi-Sentence Inference

2022

RoBERTa-Base Joint MSPP

amazon-research/wqa-multi-sentence-inference

Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection

2022

RoBERTa-Base + SSP

A Compare-Aggregate Model with Latent Clustering for Answer Selection

2019

Comp-Clip + LM + LC

Simple and Effective Text Matching with Richer Alignment Features

2019

RE2

alibaba-edu/simple-effective-text-matching hitvoice/RE2 alibaba-edu/simple-effective-text-matching-pytorch

Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering

2017

HyperQA

vanzytay/WSDM2018_HyperQA

Key-Value Memory Networks for Directly Reading Documents

2016

Key-Value Memory Network

facebookresearch/ParlAI jojonki/key-value-memory-networks

Sentence Similarity Learning by Lexical Decomposition and Composition

2016

LDC

Leputa/CIKM-AnalytiCup-2018

Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency

2018

PairwiseRank + Multi-Perspective CNN

Neural Variational Inference for Text Processing

2015

Attentive LSTM

carpedm20/variational-text-tensorflow jiacheng-xu/vmf_vae_nlp

Attentive Pooling Networks

2016

AP-CNN

winter1997/Attentive-Pooling-Networks zhaojinglong/Attentive-Pooling-Networks iamwinter/Attentive-Pooling-Networks

Neural Variational Inference for Text Processing

2015

LSTM (lexical overlap + dist output)

carpedm20/variational-text-tensorflow jiacheng-xu/vmf_vae_nlp

Neural Semantic Encoders

2016

MMA-NSE attention

Smerity/keras_snli tsendeemts/nse saraswat/munkhdalai-nse

Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms

2018

SWEM-concat

dinghanshen/SWEM nyk510/scdv-python

Neural Variational Inference for Text Processing

2015

LSTM

carpedm20/variational-text-tensorflow jiacheng-xu/vmf_vae_nlp

Deep Learning for Answer Sentence Selection

2014

Bigram-CNN (lexical overlap + dist output)

brmson/dataset-sts umutguneri/Question-Answering-Assistant

Deep Learning for Answer Sentence Selection

2014

Bigram-CNN

brmson/dataset-sts umutguneri/Question-Answering-Assistant

Distributed Representations of Sentences and Documents

2014

Paragraph vector (lexical overlap + dist output)

inejc/paragraph-vectors eske/multivec

Distributed Representations of Sentences and Documents

2014

Paragraph vector

inejc/paragraph-vectors eske/multivec

WikiQA

Performance Over Time

Edit Benchmark Results

Edit Result

Top Performing Models

All Papers (23)

Structural Self-Supervised Objectives for Transformers

RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm

TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection

Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection

Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection

Paragraph-based Transformer Pre-training for Multi-Sentence Inference

Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection

A Compare-Aggregate Model with Latent Clustering for Answer Selection

Simple and Effective Text Matching with Richer Alignment Features

Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering

Key-Value Memory Networks for Directly Reading Documents

Sentence Similarity Learning by Lexical Decomposition and Composition

Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency

Neural Variational Inference for Text Processing

Attentive Pooling Networks

Neural Variational Inference for Text Processing

Neural Semantic Encoders

Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms

Neural Variational Inference for Text Processing

Deep Learning for Answer Sentence Selection

Deep Learning for Answer Sentence Selection

Distributed Representations of Sentences and Documents

Distributed Representations of Sentences and Documents

Model	Paper	MAP	Date
TANDA-DeBERTa-V3-Large + ALL	Structural Self-Supervised Objectives for Transfo…	0.93	2023-09-15
RLAS-BIABC	RLAS-BIABC: A Reinforcement Learning-Based Answer…	0.92	2023-01-07
TANDA-RoBERTa (ASNQ, WikiQA)	TANDA: Transfer and Adapt Pre-Trained Transformer…	0.92	2019-11-11
DeBERTa-V3-Large + ALL	Pre-training Transformer Models with Sentence-Lev…	0.91	2022-05-20
DeBERTa-Large + SSP	Pre-training Transformer Models with Sentence-Lev…	0.90	2022-05-20
RoBERTa-Base Joint MSPP	Paragraph-based Transformer Pre-training for Mult…	0.89	2022-05-02
RoBERTa-Base + SSP	Pre-training Transformer Models with Sentence-Lev…	0.89	2022-05-20
Comp-Clip + LM + LC	A Compare-Aggregate Model with Latent Clustering …	0.76	2019-05-30
RE2	Simple and Effective Text Matching with Richer Al…	0.75	2019-08-01
HyperQA	Hyperbolic Representation Learning for Fast and E…	0.71	2017-07-25
Key-Value Memory Network	Key-Value Memory Networks for Directly Reading Do…	0.71	2016-06-09
LDC	Sentence Similarity Learning by Lexical Decomposi…	0.71	2016-02-23
PairwiseRank + Multi-Perspective CNN	Noise Contrastive Estimation and Negative Samplin…	0.70	2018-09-06
Attentive LSTM	Neural Variational Inference for Text Processing	0.69	2015-11-19
AP-CNN	Attentive Pooling Networks	0.69	2016-02-11
LSTM (lexical overlap + dist output)	Neural Variational Inference for Text Processing	0.68	2015-11-19
MMA-NSE attention	Neural Semantic Encoders	0.68	2016-07-14
SWEM-concat	Baseline Needs More Love: On Simple Word-Embeddin…	0.68	2018-05-24
LSTM	Neural Variational Inference for Text Processing	0.66	2015-11-19
Bigram-CNN (lexical overlap + dist output)	Deep Learning for Answer Sentence Selection	0.65	2014-12-04
Bigram-CNN	Deep Learning for Answer Sentence Selection	0.62	2014-12-04
Paragraph vector (lexical overlap + dist output)	Distributed Representations of Sentences and Docu…	0.60	2014-05-16
Paragraph vector	Distributed Representations of Sentences and Docu…	0.51	2014-05-16