Text Adaptation to Plain Language and Easy Read via Automatic Post-Editing Cycles
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908539671281664 |
|---|---|
| author | Calleja, Jesús Ponce, David Etchegoyhen, Thierry |
| author_facet | Calleja, Jesús Ponce, David Etchegoyhen, Thierry |
| contents | We describe Vicomtech's participation in the CLEARS challenge on text adaptation to Plain Language and Easy Read in Spanish. Our approach features automatic post-editing of different types of initial Large Language Model adaptations, where successive adaptations are generated iteratively until readability and similarity metrics indicate that no further adaptation refinement can be successfully performed. Taking the average of all official metrics, our submissions achieved first and second place in Plain language and Easy Read adaptation, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11991 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Text Adaptation to Plain Language and Easy Read via Automatic Post-Editing Cycles Calleja, Jesús Ponce, David Etchegoyhen, Thierry Computation and Language Artificial Intelligence We describe Vicomtech's participation in the CLEARS challenge on text adaptation to Plain Language and Easy Read in Spanish. Our approach features automatic post-editing of different types of initial Large Language Model adaptations, where successive adaptations are generated iteratively until readability and similarity metrics indicate that no further adaptation refinement can be successfully performed. Taking the average of all official metrics, our submissions achieved first and second place in Plain language and Easy Read adaptation, respectively. |
| title | Text Adaptation to Plain Language and Easy Read via Automatic Post-Editing Cycles |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.11991 |