activity
20182020
most citedAdding Interpretable Attention to Neural Translation Models Improves Word Alignment

79 citations · 79 across the 2 of their papers we have counts for

collaborators

5 papers

cs.CL2020

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…

cs.CL2020

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…

cs.CL201979 cited

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…

cs.CL2019

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…

cs.CL2018

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…