arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.10909cs.CL
收藏

BERT用于接缝意图分类和槽填充

BERT for Joint Intent Classification and Slot Filling

Speech Lab, DAMO Academy, Alibaba Group(达摩院,阿里巴巴集团,语音实验室)

Qian Chen, Zhu Zhuo, Wen Wang

摘要:

意图分类和槽填充是自然语言理解的两个基本任务。它们通常受到小规模人类标记的训练数据的影响,导致泛化能力差,特别是对于稀有词。最近,一种新的语言表示模型,BERT(来自Transformers的双向编码器表示),有助于在大规模未标记语料库上预训练深度双向表示,并在简单的微调后为各种各样的自然语言处理任务创建了最先进的模型。然而,还没有太多的努力,探索BERT的自然语言的理解。本文提出了一种基于BERT的联合意图分类和时隙填充模型。实验结果表明,与基于注意力的递归神经网络模型和槽门模型相比,该模型在多个公共基准数据集上的意图分类准确率、槽填充F1和句子级语义框架准确率都有显著提高.

英文摘要:

Intent classification and slot filling are two essential tasks for natural language understanding. They often suffer from small-scale human-labeled training data, resulting in poor generalization capability, especially for rare words. Recently a new language representation model, BERT (Bidirectional Encoder Representations from Transformers), facilitates pre-training deep bidirectional representations on large-scale unlabeled corpora, and has created state-of-the-art models for a wide variety of natural language processing tasks after simple fine-tuning. However, there has not been much effort on exploring BERT for natural language understanding. In this work, we propose a joint intent classification and slot filling model based on BERT. Experimental results demonstrate that our proposed model achieves significant improvement on intent classification accuracy, slot filling F1, and sentence-level semantic frame accuracy on several public benchmark datasets, compared to the attention-based recurrent neural network models and slot-gated models.

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。

↑