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 in:arXiv.org 2021-08
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: Article
Language:English
Subjects:
Canonical forms
Natural language
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
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