CoQA

Conversational Question Answering Challenge

Dataset Information
Modalities
Texts
Languages
English
Introduced
2018
Homepage

Overview

CoQA is a large-scale dataset for building Conversational Question Answering systems. The goal of the CoQA challenge is to measure the ability of machines to understand a text passage and answer a series of interconnected questions that appear in a conversation.

CoQA contains 127,000+ questions with answers collected from 8000+ conversations. Each conversation is collected by pairing two crowdworkers to chat about a passage in the form of questions and answers. The unique features of CoQA include 1) the questions are conversational; 2) the answers can be free-form text; 3) each answer also comes with an evidence subsequence highlighted in the passage; and 4) the passages are collected from seven diverse domains. CoQA has a lot of challenging phenomena not present in existing reading comprehension datasets, e.g., coreference and pragmatic reasoning.

Source: https://stanfordnlp.github.io/coqa/
Image Source: https://stanfordnlp.github.io/coqa/

Variants: CoQA

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Question Answering GPT-3 175B (few-shot, k=32) Language Models are Few-Shot Learners 2020-05-28
Question Answering SDNet (ensemble) SDNet: Contextualized Attention-based Deep Network … 2018-12-10
Question Answering SDNet (single model) SDNet: Contextualized Attention-based Deep Network … 2018-12-10
Question Answering BERT Large Augmented (single model) BERT: Pre-training of Deep Bidirectional … 2018-10-11
Question Answering BERT-base finetune (single model) BERT: Pre-training of Deep Bidirectional … 2018-10-11
Question Answering FlowQA (single model) FlowQA: Grasping Flow in History … 2018-10-06
Question Answering BiDAF++ (single model) A Qualitative Comparison of CoQA, … 2018-09-27
Question Answering Vanilla DrQA (single model) CoQA: A Conversational Question Answering … 2018-08-21
Question Answering DrQA + seq2seq with copy attention (single model) CoQA: A Conversational Question Answering … 2018-08-21

Research Papers

Recent papers with results on this dataset: