SpeechRE
论文信息
标题:Towards Relation Extraction From Speech
作者:Tongtong Wu, Guitao Wang, Jinming Zhao, Zhaoran Liu, Guilin Qi, Yuan-Fang Li, Gholamreza Haffari
期刊:EMNLP 2022
发布时间与更新时间:2022.10.17
主题:自然语言处理、关系抽取、口语理解、SpeechRE、SLU
arXiv:[2210.08759] Towards Relation Extraction From Speech (arxiv.org)
代码:wutong8023/SpeechRE (github.com)文章来源:https://uudwc.com/A/9d1VB
概述
口语理解(Spoken Language Understanding,SLU)的目的是从话语中提取关键信息,它被广泛应用于语音搜索和会议总结。SLU 主要包括意图检测(intent detection)和槽位填充(slot filling),而语音关系抽取(Speech Relation Extraction,SpeechRE)是一项新的**同时包含实体识别(NER)和关系提取(RE)**的口语理解任务文章来源地址https://uudwc.com/A/9d1VB