Papers by Eliana Colunga
On the Automatic Generation and Simplification of Children’s Stories (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have made it possible to generate children's educational texts with appropriate lexical and readability levels. |
| Approach: | They first examine the ability of several popular LLMs to generate stories with properly adjusted lexical and readability levels. |
| Outcome: | The proposed models can generalize to the domain of children's stories and create an efficient pipeline for their automatic generation. |
Representing the Toddler Lexicon: Do the Corpus and Semantics Matter? (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing studies on child language development have relied on adult-based measures to model their lexicons. |
| Approach: | They propose to use transcripts of child-directed conversations, picture books and dialog from G-rated movies to approximate the language input a North American preschooler might hear. |
| Outcome: | The proposed model outperforms models based on the existing corpus and the existing model. |
Measuring Contextual Informativeness in Child-Directed Text (2025.coling-main)
Copied to clipboard
Maria R. Valentini, Téa Y. Wright, Ali Marashian, Jennifer M. Ellis, Eliana Colunga, Katharina von der Wense
| Challenge: | Recent advances in natural language processing (NLP) have made it possible to generate children's stories with a single word. |
| Approach: | They propose a task of measuring contextual informativeness in children's stories and a large language model to automate the task. |
| Outcome: | The proposed method outperforms baselines and can generalize to measuring contextual informativeness in adult-directed text. |
Morphological Processing of Low-Resource Languages: Where We Are and What’s Next (2022.findings-acl)
Copied to clipboard
Adam Wiemerslage, Miikka Silfverberg, Changbing Yang, Arya McCarthy, Garrett Nicolai, Eliana Colunga, Katharina Kann
| Challenge: | Existing models for morphological processing are not suitable for low-resource languages, but they are still lacking in the field of computational morphology. |
| Approach: | They propose to bridge two unsupervised models to understand a language’s morphology from raw text alone and propose to use them to improve their models. |
| Outcome: | The proposed models perform reasonably, but there is room for improvement. |