SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2501–2525 of 10817 papers

TitleStatusHype
Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR—0
Character Matters: Video Story Understanding with Character-Aware Relations—0
ARES: A Reading Comprehension Ensembling Service—0
Al-Bayan: An Arabic Question Answering System for the Holy Quran—0
Characterizing Video Question Answering with Sparsified Inputs—0
Are Sample-Efficient NLP Models More Robust?—0
Adaptations of ROUGE and BLEU to Better Evaluate Machine Reading Comprehension Task—0
On the Need of Cross Validation for Discourse Relation Classification—0
Al-Bayan: A Knowledge-based System for Arabic Answer Selection—0
Characterizing Misclassifications of Deep NLP Models—0
ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs—0
Characterizing Interactions and Relationships between People—0
Characterizing Datasets for Social Visual Question Answering, and the New TinySocial Dataset—0
A Reranking Model for Discourse Segmentation using Subtree Features—0
Double Topic Shifts in Open Domain Conversations: Natural Language Interface for a Wikipedia-based Robot Application—0
Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan—0
Do Transformers Dream of Inference, or Can Pretrained Generative Models Learn Implicit Inferential Rules?—0
Character based String Kernels for Bio-Entity Relation Detection—0
Double Retrieval and Ranking for Accurate Question Answering—0
Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness—0
Do We Need to Differentiate Negative Candidates Before Training a Neural Ranker?—0
DP-KB: Data Programming with Knowledge Bases Improves Transformer Fine Tuning for Answer Sentence Selection—0
DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering—0
Character-Aware Neural Networks for Arabic Named Entity Recognition for Social Media—0
Changing Answer Order Can Decrease MMLU Accuracy—0
Show:102550
← PrevPage 101 of 433Next →
All datasetsSQuAD2.0SQuAD1.1HotpotQAPIQABoolQCOPATriviaQASQuAD1.1 devNatural QuestionsOpenBookQATruthfulQAMultiRC

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1IE-Net (ensemble)EM90.94—Unverified
2FPNet (ensemble)EM90.87—Unverified
3IE-NetV2 (ensemble)EM90.86—Unverified
4SA-Net on Albert (ensemble)EM90.72—Unverified
5SA-Net-V2 (ensemble)EM90.68—Unverified
6FPNet (ensemble)EM90.6—Unverified
7Retro-Reader (ensemble)EM90.58—Unverified
8EntitySpanFocusV2 (ensemble)EM90.52—Unverified
9TransNets + SFVerifier + SFEnsembler (ensemble)EM90.49—Unverified
10EntitySpanFocus+AT (ensemble)EM90.45—Unverified