arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.11060cs.CL
收藏

基于上下文感知神经网络的自动生成对话行为分类

Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions

Institute for Natural Language Processing (IMS), University of Stuttgart(斯图加特大学自然语言处理研究所(IMS))

Daniel Ortega, Chia-Yu Li, Gisela Vallejo, Pavel Denisov, Ngoc Thang Vu

摘要:

本文介绍了我们的最新研究的对话行为(DA)分类自动生成的transmittance。我们提出了一种新的方法,结合卷积神经网络(CNN)和条件随机场(CRF)的上下文建模DA分类。我们探讨了从不同的自动语音识别系统,如混合TDNN/HMM和端到端系统的最终性能产生的transmittance的影响。在两个基准数据集(MRDA和SwDA)上的实验结果表明,CNN和CRF的组合一致地提高了准确率。此外,他们表明,虽然单词出错率是可比的,端到端ASR系统似乎更适合DA分类。

英文摘要:

This paper presents our latest investigations on dialog act (DA) classification on automatically generated transcriptions. We propose a novel approach that combines convolutional neural networks (CNNs) and conditional random fields (CRFs) for context modeling in DA classification. We explore the impact of transcriptions generated from different automatic speech recognition systems such as hybrid TDNN/HMM and End-to-End systems on the final performance. Experimental results on two benchmark datasets (MRDA and SwDA) show that the combination CNN and CRF improves consistently the accuracy. Furthermore, they show that although the word error rates are comparable, End-to-End ASR system seems to be more suitable for DA classification.

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。

↑