Noise Robust Named Entity Understanding for Voice Assistants
This addresses noise robustness in voice assistants for users, but it is incremental as it builds on existing methods with specific gains.
The paper tackled the problem of named entity recognition and linking in voice assistants by proposing a joint reranking architecture, resulting in improvements of up to 3.13% in NER F1 score and up to 3.6% in EL F1 score.
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.