TrecQA

Text Retrieval Conference Question Answering

Dataset Information
Modalities
Texts
Introduced
2007
License
Unknown
Homepage
Official Website
Contents

Overview

Text Retrieval Conference Question Answering (TrecQA) is a dataset created from the TREC-8 (1999) to TREC-13 (2004) Question Answering tracks. There are two versions of TrecQA: raw and clean. Both versions have the same training set but their development and test sets differ. The commonly used clean version of the dataset excludes questions in development and test sets with no answers or only positive/negative answers. The clean version has 1,229/65/68 questions and 53,417/1,117/1,442 question-answer pairs for the train/dev/test split.

Source: A Gated Self-attention Memory Network for Answer Selection

Variants: TrecQA, trec

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Question Answering TANDA DeBERTa-V3-Large + ALL Structural Self-Supervised Objectives for Transformers 2023-09-15
Question Answering Contextual DeBERTa-V3-Large + SSP Context-Aware Transformer Pre-Training for Answer … 2023-05-24
Question Answering RLAS-BIABC RLAS-BIABC: A Reinforcement Learning-Based Answer … 2023-01-07
Question Answering RoBERTa-Base + PSD Pre-training Transformer Models with Sentence-Level … 2022-05-20
Question Answering DeBERTa-V3-Large + SSP Pre-training Transformer Models with Sentence-Level … 2022-05-20
Question Answering RoBERTa-Base Joint + MSPP Paragraph-based Transformer Pre-training for Multi-Sentence … 2022-05-02
Question Answering TANDA-RoBERTa (ASNQ, TREC-QA) TANDA: Transfer and Adapt Pre-Trained … 2019-11-11
Question Answering NLP-Capsule Towards Scalable and Reliable Capsule … 2019-06-06
Question Answering Comp-Clip + LM + LC A Compare-Aggregate Model with Latent … 2019-05-30
Question Answering aNMM aNMM: Ranking Short Answer Texts … 2018-01-05
Question Answering HyperQA Hyperbolic Representation Learning for Fast … 2017-07-25
Question Answering CNN Deep Learning for Answer Sentence … 2014-12-04

Research Papers

Recent papers with results on this dataset:

External Links: