5 papers
OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion
Sai Koneru, Matthias Huck, Jan Niehues
There has been significant progress in open-source text-only translation large language models (LLMs) with better language coverage and quality. However, these models can be only u…
Learning to Translate Ambiguous Terminology by Preference Optimization on Post-Edits
Nathaniel Berger, Johannes Eschbach-Dymanus, Miriam Exel +2
In real world translation scenarios, terminology is rarely one-to-one. Instead, multiple valid translations may appear in a terminology dictionary, but correctness of a translation…
Quality-Aware Decoding: Unifying Quality Estimation and Decoding
Sai Koneru, Matthias Huck, Miriam Exel +1
Quality Estimation (QE) models for Neural Machine Translation (NMT) predict the quality of the hypothesis without having access to the reference. An emerging research direction in…
Post-edits Are Preferences Too
Nathaniel Berger, Miriam Exel, Matthias Huck +1
Preference Optimization (PO) techniques are currently one of the state of the art techniques for fine-tuning large language models (LLMs) on pairwise preference feedback from human…
Plug, Play, and Fuse: Zero-Shot Joint Decoding via Word-Level Re-ranking Across Diverse Vocabularies
Sai Koneru, Matthias Huck, Miriam Exel +1
Recent advancements in NLP have resulted in models with specialized strengths, such as processing multimodal inputs or excelling in specific domains. However, real-world tasks, lik…