ADiEU: Toward Domain-Based Evaluation of Spoken Dialog Systems

被引:0
作者
Kleindienst, Jan [1 ]
Curin, Jan [1 ]
Labsky, Martin [1 ]
机构
[1] IBM Res Corp, Prague, Czech Republic
来源
HUMAN-COMPUTER INTERACTION, PT I | 2009年 / 5610卷
关键词
Dialog; evaluation; scoring; multimodal; speech recognition;
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
We propose a new approach toward evaluation of spoken dialog systems. The novelty of our method is based on utilization of domain-specific knowledge combined with the deterministic measurement of dialog system performance on a set of individual tasks within the domain. The proposed methodology thus attempts to answer questions such as: "How well is my dialog system performing on a specific domain?", "How much has my dialog system improved since the previous version?", "How much is my dialog system better/worse than other dialog systems performing on that domain?"
引用
收藏
页码:287 / 294
页数:8
相关论文
共 11 条
[1]  
ALLEN J, 2007, 22 C ART INT
[2]  
Carroll JohnM., 2001, Human-Computer Interaction in the New Millennium
[3]  
CASSELL J, 2002, IMAGINA 2002
[4]  
Gandhe Sudeep, 2008, Proc. of SIGdial08, P172
[5]  
Graesser AC, 2001, AI MAG, V22, P39
[6]   The PARADISE evaluation framework: Issues and findings [J].
Hajdinjak, Melita ;
Mihelic, France .
COMPUTATIONAL LINGUISTICS, 2006, 32 (02) :263-272
[7]  
Jurafsky D., 2018, SPEECH LANGUAGE PROC
[8]  
LEBIGOT L, 2008, HUMAN COMPUTER INTER, P269
[9]  
Nielsen Jakob, 1994, USABILITY INSPECTION, P25, DOI [10.5555/189200.189209, DOI 10.5555/189200.189209, DOI 10.1089/TMJ.2010.0114]
[10]  
Walker M., 2000, Natural Language Engineering, V6, P363, DOI 10.1017/S1351324900002503