arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08701cs.CL
收藏

用于丰富自然语言理解的意图特征

Intent Features for Rich Natural Language Understanding

Interactions;University of Copenhagen(哥本哈根大学)

Brian Lester, Sagnik Ray Choudhury, Rashmi Prasad, Srinivas Bangalore

摘要:

对话系统中的复杂自然语言理解模块具有对用户话语的更丰富的理解,并且因此在提供更好的用户体验方面是至关重要的。然而,这些模型通常是为特定的客户端和用例从头开始创建的,并且需要对大型数据集进行注释。这鼓励在多个客户端之间共享带注释的数据。为了促进这一点,我们引入了意图特征的概念:只能从句法线索中学习的意图的域和主题不可知属性,因此可以共享。我们引入了一种新的神经网络架构,全局-局部模型,该模型在部署的多意图自然语言理解模块中识别这些特征的强基线上显示出显着的改进,并且更一般地说,在分类设置中,必须利用整个上下文对话语的一部分进行分类。

英文摘要:

Complex natural language understanding modules in dialog systems have a richer understanding of user utterances, and thus are critical in providing a better user experience. However, these models are often created from scratch, for specific clients and use cases, and require the annotation of large datasets. This encourages the sharing of annotated data across multiple clients. To facilitate this we introduce the idea of intent features: domain and topic agnostic properties of intents that can be learned from the syntactic cues only, and hence can be shared. We introduce a new neural network architecture, the Global-Local model, that shows significant improvement over strong baselines for identifying these features in a deployed, multi-intent natural language understanding module, and, more generally, in a classification setting where a part of an utterance has to be classified utilizing the whole context.

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。

↑