Measuring Contextual Informativeness in Child-Directed Text
This addresses a gap in creating educational children's stories for vocabulary enrichment, though it appears incremental as it applies existing LLM technology to a new domain-specific task.
The paper tackles the problem of automatically evaluating how well children's stories convey the semantics of target vocabulary words for educational content generation, proposing an LLM-based method that achieves a Spearman correlation of 0.4983 with human judgments, outperforming baselines at 0.3534.
To address an important gap in creating children's stories for vocabulary enrichment, we investigate the automatic evaluation of how well stories convey the semantics of target vocabulary words, a task with substantial implications for generating educational content. We motivate this task, which we call measuring contextual informativeness in children's stories, and provide a formal task definition as well as a dataset for the task. We further propose a method for automating the task using a large language model (LLM). Our experiments show that our approach reaches a Spearman correlation of 0.4983 with human judgments of informativeness, while the strongest baseline only obtains a correlation of 0.3534. An additional analysis shows that the LLM-based approach is able to generalize to measuring contextual informativeness in adult-directed text, on which it also outperforms all baselines.