Texts

ReQA

Retrieval Question-Answering

Introduced in ReQA: An Evaluation for End-to-End Answer Retrieval Models2019

About this Dataset

Retrieval Question-Answering (ReQA) benchmark tests a model’s ability to retrieve relevant answers efficiently from a large set of documents.

Source: ReQA: An Evaluation for End-to-End Answer Retrieval Models

Dataset Variants

ReQA

Papers1

ReQA: An Evaluation for End-to-End Answer Retrieval Models

Retrieval Question Answering (ReQA), a benchmark for evaluating large-scale sentence- and paragraph-level answer retrieval models, is introduced and baselines are established using both neural encoding models as well as classical information retrieval techniques.

Dataset Loaders

EDIT

📦

google/retrieval-qa-eval

tf

Tasks

EDIT

Question Answering Information Retrieval Learning-To-Rank

Similar Datasets