# Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering

Source: [Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering](<https://www.sota2.com/research/paper/68fa6a3f1e209131cea26ff4>)

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

Data updated: 2026-01-04T05:10:03.946Z

Authors: Gangwoo Kim, Hyunjae Kim, Jungsoo Park, Jaewoo Kang

Published: 2021-06-22T07:16:45.000Z

## Abstract

One of the main challenges in conversational question answering (CQA) is to resolve the conversational dependency, such as anaphora and ellipsis. However, existing approaches do not explicitly train QA models on how to resolve the dependency, and thus these models are limited in understanding human dialogues. In this paper, we propose a novel framework, ExCorD (Explicit guidance on how to resolve Conversational Dependency) to enhance the abilities of QA models in comprehending conversational context. ExCorD first generates self-contained questions that can be understood without the conversation history, then trains a QA model with the pairs of original and self-contained questions using a consistency-based regularizer. In our experiments, we demonstrate that ExCorD significantly improves the QA models' performance by up to 1.2 F1 on QuAC, and 5.2 F1 on CANARD, while addressing the limitations of the existing approaches.

## 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 QuAC](<https://www.sota2.com/research/sota/conversational-question-answering-on-quac.md>): Conversational Question Answering; QuAC; F1 Score: 67.7.

- [Conversational Question Answering on CANARD](<https://www.sota2.com/research/sota/conversational-question-answering-on-canard.md>): Conversational Question Answering; CANARD; F1 Score: 0.681.

- [Conversational Question Answering on CoQA without human rewrites v1.0 (test)](<https://www.sota2.com/research/sota/conversational-question-answering-on-coqa-without-human-rewrites-v1-0-test.md>): Conversational Question Answering; CoQA without human rewrites v1.0 (test); Overall F1: 83.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2106.11575>)

[PDF](<https://arxiv.org/pdf/2106.11575.pdf>)

[Implementation](<https://github.com/dmis-lab/excord>)