Towards End-to-End Open Conversational Machine Reading

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhou, Sizhe, Ouyang, Siru, Zhang, Zhuosheng, Zhao, Hai
Format: Preprint
Publié: 2022
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929557503737856
author Zhou, Sizhe
Ouyang, Siru
Zhang, Zhuosheng
Zhao, Hai
author_facet Zhou, Sizhe
Ouyang, Siru
Zhang, Zhuosheng
Zhao, Hai
contents In open-retrieval conversational machine reading (OR-CMR) task, machines are required to do multi-turn question answering given dialogue history and a textual knowledge base. Existing works generally utilize two independent modules to approach this problem's two successive sub-tasks: first with a hard-label decision making and second with a question generation aided by various entailment reasoning methods. Such usual cascaded modeling is vulnerable to error propagation and prevents the two sub-tasks from being consistently optimized. In this work, we instead model OR-CMR as a unified text-to-text task in a fully end-to-end style. Experiments on the ShARC and OR-ShARC dataset show the effectiveness of our proposed end-to-end framework on both sub-tasks by a large margin, achieving new state-of-the-art results. Further ablation studies support that our framework can generalize to different backbone models.
format Preprint
id arxiv_https___arxiv_org_abs_2210_07113
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Towards End-to-End Open Conversational Machine Reading
Zhou, Sizhe
Ouyang, Siru
Zhang, Zhuosheng
Zhao, Hai
Computation and Language
Artificial Intelligence
Human-Computer Interaction
Information Retrieval
Machine Learning
In open-retrieval conversational machine reading (OR-CMR) task, machines are required to do multi-turn question answering given dialogue history and a textual knowledge base. Existing works generally utilize two independent modules to approach this problem's two successive sub-tasks: first with a hard-label decision making and second with a question generation aided by various entailment reasoning methods. Such usual cascaded modeling is vulnerable to error propagation and prevents the two sub-tasks from being consistently optimized. In this work, we instead model OR-CMR as a unified text-to-text task in a fully end-to-end style. Experiments on the ShARC and OR-ShARC dataset show the effectiveness of our proposed end-to-end framework on both sub-tasks by a large margin, achieving new state-of-the-art results. Further ablation studies support that our framework can generalize to different backbone models.
title Towards End-to-End Open Conversational Machine Reading
topic Computation and Language
Artificial Intelligence
Human-Computer Interaction
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2210.07113