典型文献
Intent-Slot Correlation Modeling for Joint Intent Prediction and Slot Filling
文献摘要：
Slot filling and intent prediction are basic tasks in capturing semantic frame of human utterances.Slots and intent have strong correlation for semantic frame parsing.For each utterance,a specific intent type is generally determined with the indication information of words having slot tags(called as slot words),and in reverse the intent type decides that words of certain categories should be used to fill as slots.However,the Intent-Slot correlation is rarely modeled explicitly in existing studies,and hence may be not fully exploited.In this paper,we model Intent-Slot correlation explicitly and propose a new framework for joint intent prediction and slot filling.Firstly,we explore the effects of slot words on intent by differentiating them from the other words,and we recognize slot words by solving a sequence labeling task with the bi-directional long short-term memory(BiLSTM)model.Then,slot recognition information is introduced into attention-based intent prediction and slot filling to improve semantic results.In addition,we integrate the Slot-Gated mechanism into slot filling to model dependency of slots on intent.Finally,we obtain slot recognition,intent prediction and slot filling by training with joint optimization.Experimental results on the benchmark Air-line Travel Information System(ATIS)and Snips datasets show that our Intent-Slot correlation model achieves state-of-the-art semantic frame performance with a lightweight structure.
文献关键词：
中图分类号：
作者姓名：
Jun-Feng Fan;Mei-Ling Wang;Chang-Liang Li;Zi-Qiang Zhu;Lu Mao
作者机构：
AI Laboratory,KingSoft Corporation,Beijing 100190,China
文献出处：
引用格式：
[1]Jun-Feng Fan;Mei-Ling Wang;Chang-Liang Li;Zi-Qiang Zhu;Lu Mao-.Intent-Slot Correlation Modeling for Joint Intent Prediction and Slot Filling)[J].计算机科学技术学报（英文版）,2022(02):309-319
A类：
utterances,Slots,utterance,Snips
B类：
Intent,Correlation,Modeling,Joint,Prediction,Filling,filling,intent,prediction,basic,tasks,capturing,semantic,human,have,strong,correlation,parsing,For,each,specific,type,generally,determined,indication,information,words,having,tags,called,reverse,decides,that,certain,categories,should,used,slots,However,rarely,modeled,explicitly,existing,studies,hence,may,not,fully,exploited,this,paper,propose,new,framework,joint,Firstly,explore,effects,by,differentiating,them,from,other,recognize,solving,sequence,labeling,bi,directional,long,short,memory,BiLSTM,Then,recognition,introduced,into,attention,improve,results,addition,integrate,Gated,mechanism,dependency,Finally,obtain,training,optimization,Experimental,benchmark,Air,line,Travel,Information,System,ATIS,datasets,show,our,achieves,state,art,performance,lightweight,structure
AB值：
0.461828
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
