Papers by Erica K. Shimomoto
Multilingual Definition Modeling (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing definition modeling tasks are mainly encoder-decoder-based, with no explicit definitions. |
| Approach: | They propose a multilingual study on definition modeling using monolingual dictionary data for four new languages. |
| Outcome: | The proposed task is based on monolingual dictionary data for four new languages . results show that multilingual models can perform on-pair with English but cannot leverage potential cross-lingual synergies . |
Hype or not? Formalizing Automatic Promotional Language Detection in Biomedical Research (2026.eacl-long)
Copied to clipboard
| Challenge: | Promotional language is a term used to undermine objective evaluation of evidence, impede research development, and erode trust in science. |
| Approach: | They propose formalized guidelines for identifying hype language and apply them to annotate a portion of the National Institutes of Health grant application corpus. |
| Outcome: | The proposed guidelines can help humans reliably annotate candidate hype adjectives and train machine learning models yield promising results. |