Computational Analysis of Child Language Transcript Data

儿童语言转录数据的计算分析

• 批准号: 8059500
• 负责人: BRIAN MACWHINNEY
• 金额: $ 0.93万
• 依托单位: CARNEGIE-MELLON UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-05-01 至 2011-09-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8059500
• 关键词: Adult; Aphasia; Area; Charge; Child; Child Language; Competence; Computer Analysis; Computer Assisted; Data; Data Set; Databases; Dependency; Development; Disease; Dysarthria; Educational process of instructing; Educational workshop; Empirical Research; Genetic Transcription; Gestures; Health; Language; Language Delays; Language Development; Language Disorders; Learning; Link; Mails; Manuals; Methods; Multimedia; Online Systems; Pattern; Phase; Published Comment; Research; Research Personnel; Sign Language; Speech; Structure; System; Systems Analysis; Techniques; Time; Training; Transcript; Work; base; computerized tools; data exchange; indexing; interoperability; lexical; programs; public health relevance; sound; symposium; syntax; tool; user-friendly; wiki

DESCRIPTION (provided by applicant): The Child Language Data Exchange System (CHILDES) Project seeks to broaden and deepen our scientific understanding of language development by providing new ways of analyzing real world face-to-face interactions. The computational tools that were developed in the previous phases of the project now constitute the primary methodological basis for new empirical research on the development of spontaneous use of a first language. This work has examined all aspects of language development, including word learning, sound learning, grammatical development, and communicative development. All of these methods and data sets are provided without charge to researchers. Moreover, the database that has been collected using these tools is now the largest spoken language database available anywhere. However, we can achieve still greater efficiency and analytic precision by building even more powerful computational tools. The next phase of this project will develop new techniques to support analytic methods in the study of language development. These methods include rapid computer-assisted transcription of interactions, automatic analysis of words into their component parts, automatic linkage of words into syntactic structures, a simple user interface for searching for patterns, a system for analyzing links between speech and gesture, web-based support for collaborative commentary between research groups, and methods for moving data between different programs for alternative analyses. In addition, we will promote the use of these programs by constructing new web-based teaching tools, a new user interface, and conducting workshops and presentations at conferences. PUBLIC HEALTH RELEVANCE To help children with language delays and disorders, we need to understand the basic facts about language learning. The CHILDES project does this by allowing rapid searching for developmental patterns across a large database of transcripts from children learning language. These tools can also be applied to other health- related areas, including the study of adult language disorders, such as aphasia and dysarthria.

描述（由申请人提供）：儿童语言数据交换系统（Childes）项目旨在通过提供分析现实世界面对面互动的新方法来扩大和加深我们对语言发展的科学理解。现在，该项目先前阶段开发的计算工具现在构成了关于自发使用第一语言的新实证研究的主要方法论基础。这项工作研究了语言发展的各个方面，包括单词学习，声音学习，语法发展和交流发展。所有这些方法和数据集都是不指控研究人员的。此外，使用这些工具收集的数据库现在是任何地方可用的最大口语数据库。但是，我们可以通过构建更强大的计算工具来达到更高的效率和分析精度。该项目的下一个阶段将开发新技术，以支持语言发展研究中的分析方法。这些方法包括对交互的快速计算机辅助转录，单词自动分析到其组成部分，单词将单词链接到句法结构中，一种简单的用户界面，用于搜索模式，一种用于分析语音和手势之间的链接的系统，基于Web的链接，基于Web的支持，用于在研究组之间进行协作的方法，以及用于在不同程序之间进行替代分析的方法之间的数据。此外，我们将通过构建新的基于Web的教学工具，新的用户界面以及在会议上进行讲习班和演示来促进这些程序的使用。公共卫生的相关性为了帮助儿童患有语言延迟和疾病，我们需要了解有关语言学习的基本事实。 Childes Project通过允许快速搜索来自儿童学习语言的大型成绩单的发展模式来实现这一目标。这些工具也可以应用于其他与健康相关的领域，包括研究成人语言障碍，例如失语和构造障碍。