The DOI matches its Crossref record; the references it cites are not checked yet.
Exploring a corpus-based approach for detecting language impairment in monolingual English-speaking children
Abstract
Objectives This paper explores the use of an automated method for analyzing narratives of monolingual English speaking children to accurately predict the presence or absence of a language impairment. The goal is to exploit corpus-based approaches inspired by the fields of natural language processing and machine learning. Methods and materials We extract a large variety of features from language samples and use them to train language models and well known machine learning algorithms as the underlying predictors. The methods are evaluated on two different datasets and three language tasks. One dataset contains samples of two spontaneous narrative tasks performed by 118 children with an average age of 13 years and a second dataset contains play sessions from over 600 younger children with an average age of 6 years. Results We compare results against a cut off baseline method and show that our results are far superior, reaching F-measures of over 85% in two of the three language tasks, and 48% in the third one. Conclusions The different experiments we present here show that corpus based approaches can yield good prediction results in the problem of language impairment detection. These findings warrant further exploration of natural language processing techniques in the field of communication disorders. Moreover, the proposed framework can be easily adapted to analyze samples in languages other than English since most of the features are language independent or can be customized w…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Classifiers that successfully identified DLD when trained on structured narrative language samples were less successful when trained on data from unstructured play sessions and personal narratives.
“For example, classifiers that successfully identified DLD when trained on structured narrative language samples were less successful when trained on data from unstructured play sessions and personal narratives (Gabani et al., 2011).”
From Early Identification of Language Disorders Using Natural Language Processing and Machine Learning: Challenges and Emerging Approaches (2025) · cites this paper as Gabani et al., 2011
Across several studies, Bayesian Network or Naïve Bayes models showed the best performance.
“Across several studies, Bayesian Network (Gabani et al., 2011; Hassanali et al., 2012a/b) or Naïve Bayes (Hassanali et al., 2013) models showed the best performance.”
From Early Identification of Language Disorders Using Natural Language Processing and Machine Learning: Challenges and Emerging Approaches (2025) · cites this paper as Gabani et al., 2011
POS taggers trained on adult language have been shown to outperform taggers trained on child speech for classifying DLD, although some manual correction of automated annotation often is required and generally expected for children's speech.
“Indeed, POS taggers trained on adult language (e.g. TnT-tagger; Brants, 2000) have been shown to outperform taggers trained on child speech (e.g., MacWhinney, 2000) for classifying DLD (Gabani et al., 2011), although some manual correction of automated annotation often is required and generally expected for children's speech.”
From Early Identification of Language Disorders Using Natural Language Processing and Machine Learning: Challenges and Emerging Approaches (2025) · cites this paper as Gabani et al., 2011
In some cases, language samples are collected years after children received a diagnosis of DLD and began receiving treatment.
“Moreover, in some cases, language samples are collected years after children received a diagnosis of DLD and began receiving treatment (Gabani et al., 2011).”
From Early Identification of Language Disorders Using Natural Language Processing and Machine Learning: Challenges and Emerging Approaches (2025) · cites this paper as Gabani et al., 2011
Language productivity and speech fluency were important predictors of DLD when the model was trained on narrative samples but were not indicative of DLD in play sessions.
“An analysis of which features were most important to model accuracy showed that language productivity and speech fluency were important predictors of DLD when the model was trained on narrative samples but were not indicative of DLD in play sessions (Gabani et al., 2011).”
From Early Identification of Language Disorders Using Natural Language Processing and Machine Learning: Challenges and Emerging Approaches (2025) · cites this paper as Gabani et al., 2011
Citations
The citation lists haven’t been fetched yet
References 70 · Cited by 18
Research works printed but not linked: 38
- Simkin, 2001, Non-word repetition and grammatical morphology: normative data for children in their final year of primary school, International Journal of Language Communication Disorders, 36, 395, 10.1080/13682820110045856 · DOI
- Gathercole, 1990, Phonological memory deficits in language disordered children: is there a causal connection?, Journal of Memory and Language, 29, 336, 10.1016/0749-596X(90)90004-J · DOI · Paper page
- Bishop, 1996, Nonword repetition as a behavioural marker for inherited language impairment: evidence from a twin study, Journal of Child Psychology and Psychiatry, 37, 391, 10.1111/j.1469-7610.1996.tb01420.x · DOI
- Gaulin, 1994, Procedure for assessing verbal working memory in normal school-age children: some preliminary data, Perceptual and Motor Skills, 79, 55, 10.2466/pms.1994.79.1.55 · DOI
- Leonard, 2007, Speed of processing, working memory, and language impairment in children, Journal of Speech, Language, and Hearing Research, 50, 408, 10.1044/1092-4388(2007/029) · DOI
- Law, 2009, Modeling developmental language difficulties from school entry into adulthood: literacy, mental health and employment outcomes, Journal of Speech, Language, and Hearing Research, 52, 1401, 10.1044/1092-4388(2009/08-0142) · DOI
- Law, 2004, The efficacy of treatment for children with developmental speech and language delay/disorder: a meta-analysis, Journal of Speech, Language, and Hearing Research, 47, 924, 10.1044/1092-4388(2004/069) · DOI
- Johnson, 1999, Fourteen-year follow-up of children with and without speech/language impairments: speech/language stability and outcomes, Journal of Speech, Language, and Hearing Research, 42, 744, 10.1044/jslhr.4203.744 · DOI
- Law, 2000, The relationship between the natural history and prevalence of primary speech and language delays: findings from a systematic review of the literature, International Journal of Language and Communication Disorders, 35, 165, 10.1080/136828200247133 · DOI
- Rescorla, 2009, Age 17 language and reading outcomes in late-talking toddlers: support for a dimensional perspective on language delay, Journal of Speech, Language, and Hearing Research, 52, 16, 10.1044/1092-4388(2008/07-0171) · DOI
- Tomblin, 1996, A system for the diagnosis of specific language impairment in kindergarten children, Journal of Speech and Hearing Research, 39, 1284, 10.1044/jshr.3906.1284 · DOI
- Peña, 1992, The application of dynamic methods to language assessment, The Journal of Special Education, 26, 269, 10.1177/002246699202600304 · DOI
- Lidz, 1994, Dynamic assessment: the model, its relevance as a nonbiased approach, and its application to Latino american preschool children, Language, Speech, and Hearing Services in Schools, 27, 367
- Peña, 2001, Reducing test bias through dynamic assessment of children's word learning ability, American Journal of Speech-Language Pathology, 10, 138, 10.1044/1058-0360(2001/014) · DOI
- Spaulding, 2006, Eligibility criteria for language impairment: is the low end of normal always appropriate?, Language, Speech, and Hearing Services in Schools, 37, 61, 10.1044/0161-1461(2006/007) · DOI
- Deevy, 2010, Extending use of the NRT to preschool-age children with and without specific language impairment, Language, Speech, and Hearing Services in Schools, 41, 277, 10.1044/0161-1461(2009/08-0096) · DOI
- Greenslade, 2009, The diagnosic accuracy and construct validity of the structured photographic expressive language test-preschool: second edition, Language, Speech, and Hearing Services in Schools, 40, 150, 10.1044/0161-1461(2008/07-0049) · DOI
- Plante, 1994, Selection of preschool language tests: a data-based approach, Language, Speech, and Hearing Services in Schools, 25, 15, 10.1044/0161-1461.2501.15 · DOI
- Hansson, 1995, Grammatical characteristics of Swedish children with SLI, Journal of Speech and Hearing Research, 38, 589, 10.1044/jshr.3803.589 · DOI
- Fletcher, 1984, Characterizing language impairment in children: an exploratory study, Language Testing, 33, 10.1177/026553228400100104 · DOI
- Bedore, 1998, Specific language impairment and grammatical morphology: a discriminant function analysis, Journal of Speech, Language, and Hearing Research, 41, 1185, 10.1044/jslhr.4105.1185 · DOI
- Restrepo, 2001, Article use in Spanish-speaking children with specific language impairment, Journal of Child Language, 433, 10.1017/S0305000901004706 · DOI
- Jacobson, 2002, Morphology in incipient bilingual Spanish-speaking preschool children with specific language impairment, Applied Psycholinguistics, 23, 23, 10.1017/S0142716402000024 · DOI
- Bedore, 2005, Verb inflections and noun phrase morphology in the spontaneous speech of Spanish-speaking children with specific language impairment, Applied Psycholinguistics, 26, 195, 10.1017/S0142716405050149 · DOI
- Solorio, 2011, Analyzing language samples of Spanish-English bilingual children for the automated prediction of language dominance, Natural Language Engineering, 17, 10.1017/S1351324910000252 · DOI
- Klee, 1992, Developmental and diagnostic characteristics of quantitative measures of children's language production, Topics in Language Disorders, 12, 28, 10.1097/00011363-199202000-00005 · DOI
- Tilstra, 2007, Productivity, fluency, and grammaticality measures from narratives: Potential indicators of language proficiency?, Communication Disorders Quarterly, 29, 43, 10.1177/1525740108314866 · DOI
- Wetherell, 2007, Narrative skills in adolescents with a history of SLI in relation to non-verbal IQ scores, Child Language Teaching & Therapy, 23, 95, 10.1177/0265659007072322 · DOI
- Rice, 1995, Specific language impairment as a period of extended optional infinitive, Journal of Speech and Hearing Research, 38, 850, 10.1044/jshr.3804.850 · DOI
- Wetherell, 2007, Narrative in adolescent specific language impairment (SLI): a comparison with peers across two different narrative genres, International Journal of Language and Communication Disorders, 42, 583, 10.1080/13682820601056228 · DOI
- Conti-Ramsden, 1997, The extent to which psychometric tests differentiate subgroups of children with SLI, Journal of Speech, Language, and Hearing Research, 40, 765, 10.1044/jslhr.4004.765 · DOI
- Conti-Ramsden, 1999, Characteristics of children attending language units in England: a national study of 7-year-olds, International Journal of Language and Communication Disorders, 34, 359, 10.1080/136828299247333 · DOI
- Paradise, 2001, Early versus late tympanostomy tube placement for persistent otitis media: developmental outcomes at age 3 years, New England Journal of Medicine, 344, 1179, 10.1056/NEJM200104193441601 · DOI
- Paradise, 2003, Otitis media and tympanostomy tube insertion during the first three years of life: developmental outcomes at the age of four years, Pediatrics, 112, 265, 10.1542/peds.112.2.265 · DOI
- Paradise, 2005, Developmental outcomes after early or delayed insertion of tympanostomy tubes, The New England Journal of Medicine, 353, 576, 10.1056/NEJMoa050406 · DOI
- Marcus, 1993, Building a large annotated corpus of English: the Penn Treebank, Computational Linguistics, 19, 313
- Parisse, 2000, Automatic disambiguation of morhphosyntax in spoken language corpora, Behavior Research Methods, Instruments, & Computers, 32, 468, 10.3758/BF03200818 · DOI
- Hall MA. Correlation based feature selection for machine learning. Ph.D. thesis, University of Waikato, Hamilton, New Zeland; 1998.
Metadata
- Authors
- Gabani, K., Solorio, T., Liu, Y., Hassanali, K.-N., & Dollaghan, C. A.
- Affiliations
- The University of Texas at Dallas (US)
- University of Alabama at Birmingham (US)
- Corresponding author
- Solorio, Thamar
- ORCID
- Solorio, Thamar
- Venue
- Artificial Intelligence in Medicine
- Publisher
- Elsevier BV
- Published
- 2011-11
- Volume
- 53
- Issue
- 3
- Pages
- 161-170
- ISSN
- 0933-3657 (ISSN-L)
- OpenAlex
- W1985692908
- Cited by
- 18
- References
- 70
- Citations by year
- 2026: 3 · 2025: 1 · 2024: 1 · 2023: 1 · 2021: 1 · 2020: 1 · 2018: 1 · 2016: 1 · 2015: 1 · 2014: 1 · 2013: 4 · 2012: 2
- FWCI
- 4.58
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Artificial Intelligence in Medicine (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Science Foundation
- Pfizer
- National Institute for Health and Care Research
- National Institute of Child Health and Human Development
- NIH Clinical Center
- Topics
- Social Sciences › Psychology › Developmental and Educational Psychology › Language Development and Disorders
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- child language assessment, narrative analysis, spontaneous narratives, play sessions, linguistic features, language models, machine learning prediction, communication disorders, cross-lingual adaptation
- MeSH terms
- Adolescent, Age Factors, Algorithms, Artificial Intelligence, Child, Child Language, Female, Humans, Intelligence, Language, Language Development, Language Disorders, Language Tests, Male, Natural Language Processing, Pattern Recognition, Automated, Play and Playthings, Narration
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
