Investigating the potential of NLP-driven linguistic and acoustic features for predicting human scores of children’s oral language proficiency
- 4 July 2021
- journal article
- research article
- Published by Taylor & Francis in Assessment in Education: Principles, Policy & Practice
- Vol. 28 (4) , 477-505
Abstract
Children’s oral language proficiency (OLP) is integral for developing literacy skills. Storytelling or retelling is often used by parents and educators to elicit children’s OLP, yet it is less commonly used for assessment purposes. Leveraged by natural language processing and machine learning, this study examined the extent to which computational linguistic and acoustic indices predict human ratings of children’s (n=184 aged 9 to 11) OLP using two story retell stimuli presented in written and aural forms. Human raters scored children’s OLP on five oral proficiency criteria: vocabulary, grammar, idea development, task-fulfilment, and speech delivery, using a 4-point scale, and linguistic and acoustic features were used to predict each criterion. Results showed the efficacy of automated indices to predict human scores of children’s OLP. This study calls for attention to discrepancies in human and machine speech delivery scores and stimulus effects on story retelling performance among children of different language backgrounds.Keywords
This publication has 63 references indexed in Scilit:
- Measuring Lexical Diversity in Narrative Discourse of People With AphasiaAmerican Journal of Speech-Language Pathology, 2013
- The promise of NLP and speech processing technologies in language assessmentLanguage Testing, 2010
- Validating automated speaking testsLanguage Testing, 2010
- On the use of perceptual Line Spectral pairs Frequencies and higher-order residual moments for Speaker IdentificationInternational Journal of Biometrics, 2010
- Modeling Local Coherence: An Entity-Based ApproachComputational Linguistics, 2008
- Data miningACM SIGMOD Record, 2002
- Speaker recognition: a tutorialProceedings of the IEEE, 1997
- Model Selection Information Criteria for Non-Nested Latent Class ModelsJournal of Educational and Behavioral Statistics, 1997
- Cross-cultural Invariance in Story RecallChild Development, 1980
- Estimating the Dimension of a ModelThe Annals of Statistics, 1978