Automatic Text Simplification (ATS) aims at rewriting texts into simpler variants while preserving their original meaning, so they can be more easily understood by different audiences. While ATS has been widely used for written texts, its application to spoken language remains unexplored, even if it is not exempt from difficulty. This study aims to characterize the edit operations performed in order to simplify French transcripts for non-native speakers. To do so, we relied on a data sample randomly extracted from the Orféo-CEFC French spontaneous speech dataset. In the absence of guidelines to direct this process, we adopted an intuitive simplification approach, so as to investigate the crafted simplifications based on expert linguists’ criteria, and to compare them with those produced by a generative AI (namely, ChatGPT). The results, analyzed quantitatively and qualitatively, reveal that the most common edits are deletions, and affect oral production aspects, like restarts or hesitations. Consequently, candidate simplifications are typically register-standardized sentences that solely include the propositional content of the input. The study also examines the alignment between human- and machine-based simplifications, revealing a moderate level of agreement, and highlighting the subjective nature of the task. The findings contribute to understanding the intricacies of simplifying spontaneous spoken language. In addition, the provision of a small-scale parallel dataset derived from such expert simplifications, Propicto-Orféo-Simple, can facilitate the evaluation of speech simplification solutions.

We present the results of our constrained submission to the WMT 2024 shared task, which focuses on translating from Spanish into two low-resource languages of Spain: Aranese (spa-arn) and Aragonese (spa-arg). Our system integrates real and synthetic data generated by large language models (e.g., BLOOMZ) and rule-based Apertium translation systems. Built upon the pre-trained NLLB system, our translation model utilizes a multistage approach, progressively refining the initial model through the sequential use of different datasets, starting with large-scale synthetic or crawled data and advancing to smaller, high-quality parallel corpora. This approach resulted in BLEU scores of 30.1 for Spanish to Aranese and 61.9 for Spanish to Aragonese.

PROPICTO is a project funded by the French National Research Agency and the Swiss National Science Foundation, that aims at creating Speech-to-Pictograph translation systems, with a special focus on French as an input language. By developing such technologies, we intend to enhance communication access for non-French speaking patients and people with cognitive impairments.