AMTA 2026
Location
- Québec City, Canada
Links
Important Dates
| Call for Papers and Presentations | 06 May |
| Call for Tutorials | 06 May |
| Call for Workshops | 15 April |
| Acceptance notification | 18 June |
| Camera ready submission | 20 July |
Calls For Papers
Topics
- Latest advances in MT
- Using Large Language Models for translation, transcreation, and other cross-lingual use cases
- Training Data: data sources, extraction, alignment, and cleaning of corpora, terminology, data augmentation, metadata extraction, multimodal data, etc.
- Adaptation and customization of MT models or LLMs for cross-lingual use cases
- Augmenting MT with ML, NLP or generative AI
- Comparative evaluation of MT systems
- MT for low resource languages
- Model distillation, compression, and on-device MT
- MT in production scenarios, robustness and deployment issues
- MT for multiple modalities (speech, sign language, video, etc.)
- MT for real-time communication (chats, social networks, etc.)
- Integration of MT and related cross-lingual technologies in translation and localization pipelines
- Output quality estimation and evaluation: tools, methods, and metrics, such as human evaluations, automatic scoring, and automatic annotation of MT output
- Detecting and preventing catastrophic errors in output
- Measuring fairness, bias, and transparency in output
- Post-editing and human-in-the-loop methods: New approaches, successes and failures, applicability to different content-types, etc.
- The interaction of translators and interpreters with MT and generative AI tools and output
- Advanced MT fine-tuning and enhancement: including pre- and post-processing; controlling style, tone of voice, gender
- Interactive and real-time adaptive MT systems: including advanced approaches to leverage TM and end-user feedback
- Business Cases: making the business case for adopting MT and related cross-lingual technologies to drive business requirements
- Ethics, policy, and regulatory trends concerning the use of MT or generative AI for cross-lingual use cases
- Cross-language information retrieval
- Source text improvement: improving the source content destined for MT through automatic tools such as grammar correction, guidelines, and NLP