# QAConv: Question Answering on Informative Conversations

Source: [QAConv: Question Answering on Informative Conversations](<https://www.sota2.com/research/paper/68fa6c591e209131cea337ac>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-01T14:32:07.704Z

Authors: Chien-Sheng Wu, Andrea Madotto, Wenhao Liu, Pascale Fung, Caiming Xiong

Published: 2021-05-14T15:53:05.000Z

## Abstract

This paper introduces QAConv, a new question answering (QA) dataset that uses conversations as a knowledge source. We focus on informative conversations, including business emails, panel discussions, and work channels. Unlike open-domain and task-oriented dialogues, these conversations are usually long, complex, asynchronous, and involve strong domain knowledge. In total, we collect 34,608 QA pairs from 10,259 selected conversations with both human-written and machine-generated questions. We use a question generator and a dialogue summarizer as auxiliary tools to collect and recommend questions. The dataset has two testing scenarios: chunk mode and full mode, depending on whether the grounded partial conversation is provided or retrieved. Experimental results show that state-of-the-art pretrained QA systems have limited zero-shot performance and tend to predict our questions as unanswerable. Our dataset provides a new training and evaluation testbed to facilitate QA on conversations research.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2105.06912>)

[PDF](<https://arxiv.org/pdf/2105.06912.pdf>)

[Implementation](<https://github.com/salesforce/QAConv>)