Enhancing Neural Disfluency Detection with Hand-crafted Features

摘要：

　　In this paper,we apply a bidirectional Long Short-Term Memory with a Conditional Random Field to the task of disfluency detection.Long-range dependencies is one of the core problems for disfluency detection.Our model handles long-range dependencies by both using the Long Short-Term Memory and hand-crafted discrete features.Experiments show that utilizing the hand-crafted discrete features significantly improves the model”s performance by achieving the state-of-the-art score of 87.1%on the Switchboard corpus.

关键词： Disfluency detection BI-LSTM-CRF Discrete features Continuous neural features

作者: Shaolei Wang Wanxiang Che Yijia Liu Ting Liu

作者单位: Research Center for Social Computing and Information Retrieval School of Computer Science and Technology Harbin Institute of Technology,China

会议类型: 国内会议

会议名称: 第十五届全国计算语言学学术会议(CCL2016)暨第四届基于自然标注大数据的自然语言处理国际学术研讨会(NLP-NABD-2016)

会议地点: 烟台

会议语种:英文

页码: 1-11

在线出版日期: 2016-10-14（万方平台首次上网日期，不代表论文的发表时间）