Question Answering

Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include SQuAD, HotPotQA, bAbI, TriviaQA, WikiQA, and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.

( Image credit: SQuAD )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 3611–3620 of 10817 papers

Title	Date	Tasks	Status	Score
ATP: Directed Graph Embedding with Asymmetric Transitivity Preservation	Nov 2, 2018	Community Question AnsweringGraph Embedding	CodeCode Available	5
Improving Quality of a Post's Set of Answers in Stack Overflow	May 30, 2020	Community Question AnsweringQuestion Answering	CodeCode Available	5
Improving Question Answering Performance Using Knowledge Distillation and Active Learning	Sep 26, 2021	Active LearningKnowledge Distillation	CodeCode Available	5
Improving Retrieval-Based Question Answering with Deep Inference Models	Dec 7, 2018	Information RetrievalNatural Language Inference	CodeCode Available	5
ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion	Jan 4, 2024	Natural Language UnderstandingNeural Architecture Search	CodeCode Available	5
Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning	Apr 6, 2022	Information RetrievalParaphrase Identification	CodeCode Available	5
Combining Data Generation and Active Learning for Low-Resource Question Answering	Nov 27, 2022	Active LearningAnswer Generation	CodeCode Available	5
Improving Machine Reading Comprehension with General Reading Strategies	Oct 31, 2018	ARCLanguage Modeling	CodeCode Available	5
Improving QA Generalization by Concurrent Modeling of Multiple Biases	Oct 7, 2020	Extractive Question-AnsweringQuestion Answering	CodeCode Available	5
Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings	May 4, 2022	Contrastive LearningData Augmentation	CodeCode Available	5

Show:10 25 50

← PrevPage 362 of 1082Next →

All datasets SQuAD2.0 SQuAD1.1 HotpotQA PIQA BoolQ COPA TriviaQA SQuAD1.1 dev Natural Questions OpenBookQA TruthfulQA MultiRC

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	IE-Net (ensemble)	EM	90.94	—	Unverified
2	FPNet (ensemble)	EM	90.87	—	Unverified
3	IE-NetV2 (ensemble)	EM	90.86	—	Unverified
4	SA-Net on Albert (ensemble)	EM	90.72	—	Unverified
5	SA-Net-V2 (ensemble)	EM	90.68	—	Unverified
6	FPNet (ensemble)	EM	90.6	—	Unverified
7	Retro-Reader (ensemble)	EM	90.58	—	Unverified
8	EntitySpanFocusV2 (ensemble)	EM	90.52	—	Unverified
9	TransNets + SFVerifier + SFEnsembler (ensemble)	EM	90.49	—	Unverified
10	EntitySpanFocus+AT (ensemble)	EM	90.45	—	Unverified