Neural Lexicons for Slot Tagging in Spoken Language Understanding
Neural Lexicons for Slot Tagging in Spoken Language Understanding
复制标题
用于口语理解中槽标记的神经词典
DOI：
10.18653/v1/n19-2011
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Kyle Williams
中科院分区：
文献类型：
--
作者：
Kyle Williams
我们探讨了在口语理解中的插槽标注的神经模型中词汇或公报的使用。我们开发了将词典信息编码为神经特征的模型，用于长短期记忆神经网络。在工业环境中经常出现的条件下，对来自智能助手的4个领域的数据进行实验，其中可能存在：1)大量的训练数据，2)有限的新领域训练数据，以及3)跨领域训练。结果表明，神经词典信息的使用显著提高了槽标注能力，F-score的提高幅度高达12%。我们的发现对如何使用词汇来提高神经槽标记模型的性能具有启示意义。
We explore the use of lexicons or gazettes in neural models for slot tagging in spoken language understanding. We develop models that encode lexicon information as neural features for use in a Long-short term memory neural network. Experiments are performed on data from 4 domains from an intelligent assistant under conditions that often occur in an industry setting, where there may be: 1) large amounts of training data, 2) limited amounts of training data for new domains, and 3) cross domain training. Results show that the use of neural lexicon information leads to a significant improvement in slot tagging, with improvements in the F-score of up to 12%. Our findings have implications for how lexicons can be used to improve the performance of neural slot tagging models.