Noise Robust Named Entity Understanding for Voice Assistants

Named Entity Recognition (NER) and Entity Linking (EL) play an essential role in voice assistant interaction, but are challenging due to the special difficulties associated with spoken user queries. In this paper, we propose a novel architecture that jointly solves the NER and EL tasks by combining...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Muralidharan, Deepak, Joel Ruben Antony Moniz, Gao, Sida, Yang, Xiao, Kao, Justine, Pulman, Stephen, Kothari, Atish, Shen, Ray, Pan, Yinying, Kaul, Vivek, Mubarak Seyed Ibrahim, Xiang, Gang, Dun, Nan, Zhou, Yidan, Andy, O, Zhang, Yuan, Chitkara, Pooja, Wang, Xuan, Patel, Alkesh, Tayal, Kushal, Zheng, Roger, Grasch, Peter, Williams, Jason D, Li, Lin
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 10.08.2021
Subjects
Canonical forms
Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Computer Science - Learning
Natural language
Online AccessGet full text

Cover

More Information
Summary:Named Entity Recognition (NER) and Entity Linking (EL) play an essential role in voice assistant interaction, but are challenging due to the special difficulties associated with spoken user queries. In this paper, we propose a novel architecture that jointly solves the NER and EL tasks by combining them in a joint reranking module. We show that our proposed framework improves NER accuracy by up to 3.13% and EL accuracy by up to 3.6% in F1 score. The features used also lead to better accuracies in other natural language understanding tasks, such as domain classification and semantic parsing.
ISSN:2331-8422
DOI:10.48550/arxiv.2005.14408