Abstract
This paper presents RACAI’s system used for the shared task of ‘Subtitling track: Subtitle Compression’ (the English to Spanish language direction), organized as part of ‘the 21st edition of The International Conference on Spoken Language Translation (IWSLT 2024)’. The proposed system consists of multiple models whose outputs are then ensembled using an algorithm, which has the purpose of maximizing the similarity of the initial and resulting text. We present the introduced datasets and the models’ training strategy, along with the reported results on the proposed test set.- Anthology ID:
- 2024.iwslt-1.9
- Volume:
- Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand (in-person and online)
- Editors:
- Elizabeth Salesky, Marcello Federico, Marine Carpuat
- Venue:
- IWSLT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 57–64
- Language:
- URL:
- https://aclanthology.org/2024.iwslt-1.9
- DOI:
- 10.18653/v1/2024.iwslt-1.9
- Cite (ACL):
- Carol-Luca Gasan and Vasile Păiș. 2024. Multi-Model System for Effective Subtitling Compression. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 57–64, Bangkok, Thailand (in-person and online). Association for Computational Linguistics.
- Cite (Informal):
- Multi-Model System for Effective Subtitling Compression (Gasan & Păiș, IWSLT 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2024.iwslt-1.9.pdf