ASLTRW 2021
Workshop on Automatic Spoken Language Translation in Real-World Settings
Location
- Online
Links
Schedule
| 9:00 | Opening** Claudio Fantinuoli & Marco Turchi |
| 9:10 | End-to-end Speech Translation at Facebook** Invited talk Juan Pino (Facebook AI) |
| 9:55 | Operating a Complex SLT System with Speakers and Human Interpreters Paper Ondřej Bojar, Vojtěch Srdečný, Rishu Kumar, Otakar Smrž, Felix Schneider, Barry Haddow, Phil Williams, Chiara Canton |
| 10:15 | Simultaneous Speech Translation for Live Subtitling: from Delay to Display Paper Alina Karakanta, Sara Papi, Matteo Negri, Marco Turchi |
| 10:35 | Post-Editing Job Profiles for Subtitlers Paper Anke Tardel, Silvia Hansen-Schirra, Jean Nitzke |
| 10:55 | Technology-Augmented Multilingual Communication Models Paper Francesco Saina |
| 11:15 | Will it take another 19 years? Cognitive Ergonomics of Computer-Assisted Interpreting (CAI) Invited talk Bart Defrancq (Ghent University) |
| 12:00 | 🍴 |
| 13:00 | CompAsS - Computer-Assisted Subtitling** Invited talk Silvia Hansen-Schirra (Mainz University) |
| 13:45 | Seed Words Based Data Selection for Language Model Adaptation Paper Roberto Gretter, Marco Matassoni, Daniele Falavigna |
| 14:05 | Recent Efforts on Automatic Dubbing** Invited talk Marcello Federico (Amazon AI) |
| 14:50 | Discussion and closing remarks** Claudio Fantinuoli & Marco Turchi |
Calls For Papers
Topics
- Latest advances in cascading and end-to-end systems
- Use of spoken language translation system in a real-world scenario
- Automatic subtitling and dubbing
- Communicative inclusion through SLT
- Automatic or semi-automatic respeaking
- Customisation of SLT systems to real-world applications
- Computer-assisted interpreting
- Data scarcity and underrepresented languages
- Potential and risks of SLT
- Ethical issues (bias, etc.)
- SLT evaluation
- Communicative-oriented evaluation of spoken language translation
- Benchmark creation
- Human-machine interaction
- Hybrid systems for spoken language translation
- Cross-lingual NER/summarization/retrieval from speech
- Automatic generation of meeting minuting