Can Question Rewriting Help Conversational Question Answering?

04/13/2022
by   Etsuko Ishii, et al.
0

Question rewriting (QR) is a subtask of conversational question answering (CQA) aiming to ease the challenges of understanding dependencies among dialogue history by reformulating questions in a self-contained form. Despite seeming plausible, little evidence is available to justify QR as a mitigation method for CQA. To verify the effectiveness of QR in CQA, we investigate a reinforcement learning approach that integrates QR and CQA tasks and does not require corresponding QR datasets for targeted CQA. We find, however, that the RL method is on par with the end-to-end baseline. We provide an analysis of the failure and describe the difficulty of exploiting QR for CQA.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/07/2022

CoQAR: Question Rewriting on CoQA

Questions asked by humans during a conversation often contain contextual...
research
09/24/2019

An Empirical Study of Content Understanding in Conversational Question Answering

With a lot of work about context-free question answering systems, there ...
research
04/14/2023

Keeping the Questions Conversational: Using Structured Representations to Resolve Dependency in Conversational Question Answering

Having an intelligent dialogue agent that can engage in conversational q...
research
06/22/2021

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

One of the main challenges in conversational question answering (CQA) is...
research
07/29/2019

Reinforced Dynamic Reasoning for Conversational Question Generation

This paper investigates a new task named Conversational Question Generat...
research
10/13/2022

Towards End-to-End Open Conversational Machine Reading

In open-retrieval conversational machine reading (OR-CMR) task, machines...

Please sign up or login with your details

Forgot password? Click here to reset