A Survey on Visual Story Generation for Images in Sequence

This work presents an analysis of the intonation competence in a group of Italian children with cochlear implant (CI). Early cochlear implantation plays a crucial role in language development for children who were born deaf in that it favours the acquisition of complex aspects of language, such as the intonation structure. A story-generation task, the Narrative Competence Task, was used to elicit children’s stories. Narrations produced by 8 early implanted children and by 16 children with typically hearing (TH) (8 one-to-one matched considering the chronological age, TH-CA, and 8 considering the hearing age, TH-HA) were analysed considering intonation features (pitch accent distribution, edge tones and inner breaks). Results show that children with CI produce intonation patterns that are similar to those of both TH-CA and TH-HA control groups. Few significant differences were found only between children with CI and children matched for TH-HA in the use of rising edge tones. These results are discussed in light of the role of cognitive development in using prosody and intonation and the importance of early CI implantation. This study shows for the first time that intonation use of early implanted children is not different from that of typically developing children with the same chronological age.

Download Full-text

Automatic Story Generation

ACM Computing Surveys ◽

10.1145/3453156 ◽

2021 ◽

Vol 54 (5) ◽

pp. 1-38

Author(s):

Arwa I. Alhussain ◽

Aqil M. Azmi

Keyword(s):

Artificial Intelligence ◽

Automatic Generation ◽

Evaluation Methods ◽

Extensive Study ◽

Computational Creativity ◽

Story Generation ◽

To Receive ◽

Shed Light

Computational generation of stories is a subfield of computational creativity where artificial intelligence and psychology intersect to teach computers how to mimic humans’ creativity. It helps generate many stories with minimum effort and customize the stories for the users’ education and entertainment needs. Although the automatic generation of stories started to receive attention many decades ago, advances in this field to date are less than expected and suffer from many limitations. This survey presents an extensive study of research in the area of non-interactive textual story generation, as well as covering resources, corpora, and evaluation methods that have been used in those studies. It also shed light on factors of story interestingness.

Download Full-text

Differentiating School-Aged Children With and Without Language Impairment Using Tense and Grammaticality Measures From a Narrative Task

Journal of Speech Language and Hearing Research ◽

10.1044/2015_jslhr-l-15-0066 ◽

2016 ◽

Vol 59 (2) ◽

pp. 317-329 ◽

Cited By ~ 21

Author(s):

Ling-Yu Guo ◽

Phyllis Schneider

Keyword(s):

Language Development ◽

Diagnostic Accuracy ◽

Language Impairment ◽

Likelihood Ratios ◽

Verb Morphology ◽

Story Generation ◽

School Aged Children ◽

Sensitive Tool ◽

Good Diagnostic Accuracy ◽

Sensitivity Specificity

Purpose To determine the diagnostic accuracy of the finite verb morphology composite (FVMC), number of errors per C-unit (Errors/CU), and percent grammatical C-units (PGCUs) in differentiating school-aged children with language impairment (LI) and those with typical language development (TL). Method Participants were 61 six-year-olds (50 TL, 11 LI) and 67 eight-year-olds (50 TL, 17 LI). Narrative samples were collected using a story-generation format. FVMC, Errors/CU, and PGCUs were computed from the samples. Results All of the three measures showed acceptable to good diagnostic accuracy at age 6, but only PGCUs showed acceptable diagnostic accuracy at age 8 when sensitivity, specificity, and likelihood ratios were considered. Conclusion FVMC, Errors/CU, and PGCUs can all be used in combination with other tools to identify school-aged children with LI. However, FVMC and Errors/CU may be an appropriate diagnostic tool up to age 6. PGCUs, in contrast, may be a sensitive tool for identifying children with LI at least up to age 8 years.

Download Full-text