# Open-Retrieval Conversational Question Answering

Source: [Open-Retrieval Conversational Question Answering](<https://www.sota2.com/research/paper/68fa67991e209131cea175a1>)

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

Data updated: 2025-10-25T22:18:12.808Z

Authors: Chen Qu, Liu Yang, Cen Chen, Minghui Qiu, W. Bruce Croft, Mohit Iyyer

Published: 2020-05-22T19:39:50.000Z

## Abstract

Conversational search is one of the ultimate goals of information retrieval. Recent research approaches conversational search by simplified settings of response ranking and conversational question answering, where an answer is either selected from a given candidate set or extracted from a given passage. These simplifications neglect the fundamental role of retrieval in conversational search. To address this limitation, we introduce an open-retrieval conversational question answering (ORConvQA) setting, where we learn to retrieve evidence from a large collection before extracting answers, as a further step towards building functional conversational search systems. We create a dataset, OR-QuAC, to facilitate research on ORConvQA. We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers. Our extensive experiments on OR-QuAC demonstrate that a learnable retriever is crucial for ORConvQA. We further show that our system can make a substantial improvement when we enable history modeling in all system components. Moreover, we show that the reranker component contributes to the model performance by providing a regularization effect. Finally, further in-depth analyses are performed to provide new insights into ORConvQA.

## 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.

- [Conversational Question Answering on TopiOCQA](<https://www.sota2.com/research/sota/conversational-question-answering-on-topiocqa.md>): Conversational Question Answering; TopiOCQA; Relative Latency: 10.95.

- [Open-Domain Conversational Question Answering on OR-QuAC (test)](<https://www.sota2.com/research/sota/open-domain-conversational-question-answering-on-or-quac-test.md>): Open-Domain Conversational Question Answering; OR-QUAC (test); F1 Score: 28.86.

- [Open-Domain Conversational Question Answering on TopiOCQA (val)](<https://www.sota2.com/research/sota/open-domain-conversational-question-answering-on-topiocqa-val.md>): Open-Domain Conversational Question Answering; TopiOCQA (val); F1: 10.67.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2005.11364>)

[PDF](<https://arxiv.org/pdf/2005.11364.pdf>)