79 citations · 83 across the 8 of their papers we have counts for
11 papers
Terminal-Bench-LILT: Multilingual Agentic Coding Benchmark Grounded in Language, Region, and Culture
Yunsu Kim, Kaden Uhlig, Ashwin Purohit +10
Most evaluations for coding agents are conducted exclusively in English, which does not reflect real-world multilingual deployment. We present Terminal-Bench-LILT, a suite of 300 a…
GAIA-v2-LILT: Multilingual Adaptation of Agent Benchmark beyond Translation
Yunsu Kim, Kaden Uhlig, Joern Wuebker
Agent benchmarks remain largely English-centric, while their multilingual versions are often built with machine translation (MT) and limited post-editing. We argue that, for agenti…
Contextual Cues in Machine Translation: Investigating the Potential of Multi-Source Input Strategies in LLMs and NMT Systems
Lia Shahnazaryan, Patrick Simianer, Joern Wuebker
We explore the impact of multi-source input strategies on machine translation (MT) quality, comparing GPT-4o, a large language model (LLM), with a traditional multilingual neural m…
Cross-lingual Human-Preference Alignment for Neural Machine Translation with Direct Quality Optimization
Kaden Uhlig, Joern Wuebker, Raphael Reinauer +1
Reinforcement Learning from Human Feedback (RLHF) and derivative techniques like Direct Preference Optimization (DPO) are task-alignment algorithms used to repurpose general, found…
Neural Machine Translation Models Can Learn to be Few-shot Learners
Raphael Reinauer, Patrick Simianer, Kaden Uhlig +2
The emergent ability of Large Language Models to use a small number of examples to learn to perform in novel domains and tasks, also called in-context learning (ICL). In this work,…
Automatic Correction of Human Translations
Jessy Lin, Geza Kovacs, Aditya Shastry +2
We introduce translation error correction (TEC), the task of automatically correcting human-generated translations. Imperfections in machine translations (MT) have long motivated s…
The Impact of Text Presentation on Translator Performance
Samuel Läubli, Patrick Simianer, Joern Wuebker +3
Widely used computer-aided translation (CAT) tools divide documents into segments such as sentences and arrange them in a side-by-side, spreadsheet-like view. We present the first…
End-to-End Neural Word Alignment Outperforms GIZA++
Thomas Zenkel, Joern Wuebker, John DeNero
Word alignment was once a core unsupervised learning task in natural language processing because of its essential role in training statistical machine translation (MT) models. Alth…
Adding Interpretable Attention to Neural Translation Models Improves Word Alignment
Thomas Zenkel, Joern Wuebker, John DeNero
Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is mos…
A Comparative Study on Vocabulary Reduction for Phrase Table Smoothing
Yunsu Kim, Andreas Guta, Joern Wuebker +1
This work systematically analyzes the smoothing effect of vocabulary reduction for phrase translation models. We extensively compare various word-level vocabularies to show that th…
Compact Personalized Models for Neural Machine Translation
Joern Wuebker, Patrick Simianer, John DeNero
We propose and compare methods for gradient-based domain adaptation of self-attentive neural machine translation models. We demonstrate that a large proportion of model parameters…