SearchQA

Dataset Information
Modalities
Texts
Languages
English
Introduced
2017
License
Unknown
Homepage
Official Website
Contents

Overview

SearchQA was built using an in-production, commercial search engine. It closely reflects the full pipeline of a (hypothetical) general question-answering system, which consists of information retrieval and answer synthesis.

Source: SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine

Variants: SearchQA

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Open-Domain Question Answering Cluster-Former (#C=512) Cluster-Former: Clustering-based Sparse Transformer for … 2020-09-13
Open-Domain Question Answering Locality-Sensitive Hashing Reformer: The Efficient Transformer 2020-01-13
Open-Domain Question Answering Multi-passage BERT Multi-passage BERT: A Globally Normalized … 2019-08-22
Open-Domain Question Answering SpanBERT SpanBERT: Improving Pre-training by Representing … 2019-07-24
Open-Domain Question Answering Sparse Attention Generating Long Sequences with Sparse … 2019-04-23
Open-Domain Question Answering DecaProp Densely Connected Attention Propagation for … 2018-11-10
Open-Domain Question Answering DECAPROP Densely Connected Attention Propagation for … 2018-11-10
Open-Domain Question Answering Focused Hierarchical RNN Focused Hierarchical RNNs for Conditional … 2018-06-12
Open-Domain Question Answering AMANDA A Question-Focused Multi-Factor Attention Network … 2018-01-25
Open-Domain Question Answering R^3 R$^3$: Reinforced Reader-Ranker for Open-Domain … 2017-08-31
Open-Domain Question Answering DrQA Reading Wikipedia to Answer Open-Domain … 2017-03-31
Open-Domain Question Answering ASR Text Understanding with the Attention … 2016-03-04

Research Papers

Recent papers with results on this dataset:

External Links: