265 citations · 1.1k across the 50 of their papers we have counts for
15 papers · 1 filter
Multi-task learning to improve natural language understanding
Stefan Constantin, Jan Niehues, Alex Waibel
Recently advancements in sequence-to-sequence neural network architectures have led to an improved natural language understanding. When building a neural network-based Natural Lang…
Jet production in charged-current deep-inelastic scattering to third order in QCD
T. Gehrmann, J. Niehues, A. Huss +2
The production of jets in charged-current deep-inelastic scattering (CC DIS) probes simultaneously the strong and the electroweak sectors of the Standard Model; its measurement pro…
Towards Fluent Translations from Disfluent Speech
Elizabeth Salesky, Susanne Burger, Jan Niehues +1
When translating from speech, special consideration for conversational speech phenomena such as disfluencies is necessary. Most machine translation training data consists of well-f…
Optimizing Segmentation Granularity for Neural Machine Translation
Elizabeth Salesky, Andrew Runge, Alex Coda +2
In neural machine translation (NMT), it is has become standard to translate using subword units to allow for an open vocabulary and improve accuracy on infrequent words. Byte-pair…
Towards one-shot learning for rare-word translation with external experts
Ngoc-Quan Pham, Jan Niehues, Alex Waibel
Neural machine translation (NMT) has significantly improved the quality of automatic translation models. One of the main challenges in current systems is the translation of rare wo…
A Hierarchical Approach to Neural Context-Aware Modeling
Patrick Huber, Jan Niehues, Alex Waibel
We present a new recurrent neural network topology to enhance state-of-the-art machine learning systems by incorporating a broader context. Our approach overcomes recent limitation…
Low-Latency Neural Speech Translation
Jan Niehues, Ngoc-Quan Pham, Thanh-Le Ha +2
Through the development of neural machine translation, the quality of machine translation systems has been improved significantly. By exploiting advancements in deep learning, syst…
Robust and Scalable Differentiable Neural Computer for Question Answering
Jörg Franke, Jan Niehues, Alex Waibel
Deep learning models are often not easily adaptable to new tasks and require task-specific adjustments. The differentiable neural computer (DNC), a memory-augmented neural network,…
NNLO QCD Corrections to Jet Production in Charged Current Deep Inelastic Scattering
J. Niehues, D. M. Walker
The production of jets in charged current deep inelastic scattering (CC DIS) constitutes a class of observables that can be used to simultaneously test perturbative predictions for…
Dijet production in diffractive deep-inelastic scattering in next-to-next-to-leading order QCD
D. Britzger, J. Currie, T. Gehrmann +3
Hard processes in diffractive deep-inelastic scattering can be described by a factorisation into parton-level subprocesses and diffractive parton distributions. In this framework,…
N3LO Corrections to Jet Production in Deep Inelastic Scattering using the Projection-to-Born Method
J. Currie, T. Gehrmann, E. W. N. Glover +3
Computations of higher-order QCD corrections for processes with exclusive final states require a subtraction method for real-radiation contributions. We present the first-ever gene…
Automated Evaluation of Out-of-Context Errors
Patrick Huber, Jan Niehues, Alex Waibel
We present a new approach to evaluate computational models for the task of text understanding by the means of out-of-context error detection. Through the novel design of our automa…
An End-to-End Goal-Oriented Dialog System with a Generative Natural Language Response Generation
Stefan Constantin, Jan Niehues, Alex Waibel
Recently advancements in deep learning allowed the development of end-to-end trained goal-oriented dialog systems. Although these systems already achieve good performance, some sim…
Self-Attentional Acoustic Models
Matthias Sperber, Jan Niehues, Graham Neubig +2
Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising resul…
Jet cross sections and transverse momentum distributions with NNLOJET
T. Gehrmann, X. Chen, J. Cruz-Martinez +9
This talk discusses recent results for next-to-next-to-leading order (NNLO) QCD corrections to jet cross sections and transverse momentum distributions. The results are obtained in…