Detecting Structural Metadata with Decision Trees and Transformation-Based Learning
Detecting Structural Metadata with Decision Trees and Transformation-Based Learning
复制标题
使用决策树和基于转换的学习检测结构元数据
DOI：
10.21236/ada457891
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
Mari Ostendorf
中科院分区：
文献类型：
--
作者：
Joungbum Kim;S. Schwarm;Mari Ostendorf
翻译后摘要：经常发生的不流利是一个显着的特点，自发讲话。检测和消除这种不流利可以大大提高自发语音转录的有用性。本文提出了一个系统，检测各种类型的disfluences和其他结构信息与线索获得的词汇和韵律信息源。具体而言，决策树和语言模型的组合用于预测句子结束和中断点，并且给定这些事件，基于转换的学习用于检测编辑不流利和会话填充。结果报告人类和自动转录的对话电话讲话。
Abstract : The regular occurrence of disfluencies is a distinguishing characteristic of spontaneous speech. Detecting and removing such disfluencies can substantially improve the usefulness of spontaneous speech transcripts. This paper presents a system that detects various types of disfluences and other structural information with cues obtained from lexical and prosodic information sources. Specifically, combinations of decision trees and language models are used to predict sentence ends and interruption points and given these events transformation based learning is used to detect edit disfluencies and conversational fillers. Results are reported on human and automatic transcripts of conversational telephone speech.