We are glad to announce that 4 papers, authored by our MT Group at FBK, have been accepted for presentation at the prestigious Association for Computational Linguistics (ACL) 2024 main conference:
- When Good and Reproducible Results are a Giant with Feet of Clay: The Importance of Software Quality in NLP by Sara Papi, Marco Gaido, Andrea Pilzer, Matteo Negri
- Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing? by Marco Gaido, Sara Papi, Matteo Negri, Luisa Bentivogli
- SBAAM! Eliminating Transcript Dependency in Automatic Subtitling by Marco Gaido, Sara Papi, Matteo Negri, Mauro Cettolo, Luisa Bentivogli
- StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection by Sara Papi, Marco Gaido, Matteo Negri, Luisa Bentivogli
As part of these works, we have already open sourced two new tools:
- pangolinn: a library to help developers finding bugs in their neural networks and newly-created models.
- SubSONAR: a tool to evaluate the quality of SRT files.
Stay tuned for more updates as we prepare to present our work at ACL 2024 and soon release the missing pre-prints and code.
