COMPUTATIONAL ANALYSIS OF CHILD LANGUAGE TRANSCRIPT DATA

Carnegie-Mellon University, Pittsburgh PA

Investigators

Linked publications & trials

Abstract

"The Computational Analysis of Child Language Transcript Data" 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 have been developed in this project constitute the computational and analytic basis for the majority of new empirical research on spontaneous interaction data in first language development. The goal of this new project is to strengthen this core and to widen its application to a richer variety of empirical phenomena. To achieve this, this proposal articulates six separate subprojects: 1.The Johnny Appleseed project seeks to disseminate the CHILDES tools to language researchers around the world. 2.The LEX project involves the construction of a keyed frequency dictionary to serve as the foundation for crosslinguistic studies of lexical and morphosyntactic development. 3.The MOR project examines morpheme usage and omission, phrasal structure, clause structures, and sentence structure. 4.The TalkBank project uses the framework of the CHILDES system to build a general system for the sharing of data on communicative interactions. This database will be relevant to large segments of the social sciences. 5.The Multimedia project develops tools for digital audio and video in transcription, coding, and analysis to support the construction of TalkBank. 6.The Codon project focuses on the construction of a fundamental annotation system for the TalkBank data set