Enhancing Machine Comprehension Using Multi-Knowledge Bases and Offline Answer Span Improving System

Machine Reading Comprehension (MRC) is a challenging but meaningful task in natural language processing (NLP) that requires us to teach a machine to read and understand a given passage and answer questions related to that passage. In this paper, we present a rich knowledge-enhanced reader (RKE-Reade...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Wangji Wanglu Jishu Xuekan = Journal of Internet Technology 2021-01, Vol.22 (5), p.1095-1107
Hauptverfasser: Feifei Xu, Feifei Xu, Feifei Xu, Wenkai Zhang, Wenkai Zhang, Haizhou Du, Haizhou Du, Shanlin Zhou
Format: Artikel
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Machine Reading Comprehension (MRC) is a challenging but meaningful task in natural language processing (NLP) that requires us to teach a machine to read and understand a given passage and answer questions related to that passage. In this paper, we present a rich knowledge-enhanced reader (RKE-Reader), a hierarchical MRC model that employs double knowledge bases with an NER system as its knowledge enhancement unit. Besides, we are the first to propose an offline answer-imporving method to help model to determine the uncertain answer without extra online training process. Our experimental results indicate that on most datasets, the RKE-Reader significantly outperforms most of the published models that do not have knowledge base, especially on datasets that need commonsense reasoning. And the ablation study also reflects that external knowledge bases and answer-selecting unit do make a positive contribution in the entire model
ISSN:1607-9264
1607-9264
2079-4029
DOI:10.53106/160792642021092205013