arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.09379cs.CL
收藏

对话状态跟踪模型的任务外训练

Out-of-Task Training for Dialog State Tracking Models

Heinrich Heine University Düsseldorf(海因里希·海涅大学(杜塞尔多夫))

Michael Heck, Carel van Niekerk, Nurul Lubis, Christian Geishauser, Hsien-Chin Lin, Marco Moresi, Milica Gašić

摘要:

对话状态跟踪(DST)遭受严重的数据稀疏。虽然许多自然语言处理(NLP)任务受益于迁移学习和多任务学习,但在对话中,这些方法受到可用数据量和对话应用程序的特殊性的限制。在这项工作中,我们成功地利用不相关的NLP任务的非对话数据训练对话状态跟踪器。这为大量不相关的NLP语料库打开了大门,以缓解DST固有的数据稀疏问题。

英文摘要:

Dialog state tracking (DST) suffers from severe data sparsity. While many natural language processing (NLP) tasks benefit from transfer learning and multi-task learning, in dialog these methods are limited by the amount of available data and by the specificity of dialog applications. In this work, we successfully utilize non-dialog data from unrelated NLP tasks to train dialog state trackers. This opens the door to the abundance of unrelated NLP corpora to mitigate the data sparsity issue inherent to DST.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑