计算机科学
背景(考古学)
领域(数学分析)
人工智能
桥(图论)
跟踪(教育)
国家(计算机科学)
自然语言处理
机器学习
语音识别
算法
古生物学
内科学
数学分析
教育学
医学
数学
生物
心理学
作者
Haoxiang Su,Sijie Feng,Hongyan Xie,Di Wu,Hao Huang,Zhongjiang He,Shuangyong Song,Ruiyu Fang,Xiaomeng Huang,Wushour Silamu
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2024-03-18
卷期号:: 12521-12525
被引量:5
标识
DOI:10.1109/icassp48485.2024.10447440
摘要
Large-scale pre-trained neural language model has facilitated to achieve the state-of-the-art performance on Dialogue State Tracking (DST) tasks. One of the existing works models the semantic correlation between the dialogue context and (domain, slot) pair encoded by BERT and make the prediction. Despite the effectiveness, they ignore the fact that there is no perfect semantic correspondence between (domain, slot) pair and the dialogue context. In this paper, we propose a domain-slot aware contrastive learning framework to solve this problem, which proposes three methods to bridge the semantic gap between the dialogue context and the (domain, slot) by constructing training sample pairs to fine-tune the BERT model and use it for base DST model. The experiments demonstrate that our proposed method has improved the performance of the baseline model on the MultiWOZ2.1 and MultiWOZ2.4 datasets, yielding competitive results.
科研通智能强力驱动
Strongly Powered by AbleSci AI