The Alignment between Language Properties and Computational Algorithms Enhances Statistical Word Segmentation: Evidence from Korean Child-Directed Speech.
{"title":"The Alignment between Language Properties and Computational Algorithms Enhances Statistical Word Segmentation: Evidence from Korean Child-Directed Speech.","authors":"Jun Ho Chai,Seongmin Mun,Eon-Suk Ko","doi":"10.1017/s0305000926100646","DOIUrl":null,"url":null,"abstract":"This study investigates whether child-directed speech (CDS) exhibits enhanced segmentability compared to adult-directed speech (ADS) and explores how specific linguistic properties of each register influence computational word segmentation performance in Korean. Employing a speaker-matched corpus of naturalistic Korean CDS and ADS, we observed that Korean CDS features shorter utterances and words, lower lexical diversity, fewer hapax legomena and interjections, a greater proportion of onomatopoeia and word play, a higher frequency of one-word utterances, and lower lexical ambiguity than ADS. Computational algorithms revealed significantly higher word segmentation F-scores for CDS than ADS, suggesting that child-oriented linguistic adaptations in CDS facilitate segmentation. This observation is further supported by statistical modelling, which indicates that the enhanced segmentability in CDS is modulated by the linguistic properties of the register. We discuss the nuanced roles of these properties in shaping the performance of segmentation algorithms.","PeriodicalId":48132,"journal":{"name":"Journal of Child Language","volume":"427 1","pages":"1-27"},"PeriodicalIF":2.1000,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Child Language","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1017/s0305000926100646","RegionNum":2,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"LINGUISTICS","Score":null,"Total":0}
引用次数: 0
Abstract
This study investigates whether child-directed speech (CDS) exhibits enhanced segmentability compared to adult-directed speech (ADS) and explores how specific linguistic properties of each register influence computational word segmentation performance in Korean. Employing a speaker-matched corpus of naturalistic Korean CDS and ADS, we observed that Korean CDS features shorter utterances and words, lower lexical diversity, fewer hapax legomena and interjections, a greater proportion of onomatopoeia and word play, a higher frequency of one-word utterances, and lower lexical ambiguity than ADS. Computational algorithms revealed significantly higher word segmentation F-scores for CDS than ADS, suggesting that child-oriented linguistic adaptations in CDS facilitate segmentation. This observation is further supported by statistical modelling, which indicates that the enhanced segmentability in CDS is modulated by the linguistic properties of the register. We discuss the nuanced roles of these properties in shaping the performance of segmentation algorithms.
期刊介绍:
A key publication in the field, Journal of Child Language publishes articles on all aspects of the scientific study of language behaviour in children, the principles which underlie it, and the theories which may account for it. The international range of authors and breadth of coverage allow the journal to forge links between many different areas of research including psychology, linguistics, cognitive science and anthropology. This interdisciplinary approach spans a wide range of interests: phonology, phonetics, morphology, syntax, vocabulary, semantics, pragmatics, sociolinguistics, or any other recognised facet of language study.