We present Text-to-OverpassQL, a task designed to facilitate a natural
l...
End-to-end automatic speech translation (AST) relies on data that combin...
Supervised learning in Neural Machine Translation (NMT) typically follow...
Incremental decision making in real-world environments is one of the mos...
Reliability of machine learning evaluation – the consistency of observed...
Data augmentation is a technique to generate new training data based on
...
JoeyS2T is a JoeyNMT extension for speech-to-text tasks such as automati...
Ensembling neural networks is a long-standing technique for improving th...
Vision and language navigation (VLN) is a challenging visually-grounded
...
End-to-end speech translation relies on data that pair source-language s...
Recently more attention has been given to adversarial attacks on neural
...
Machine learning algorithms train models from patterns of input data and...
In semantic parsing of geographical queries against real-world databases...
We propose an on-the-fly data augmentation method for automatic speech
r...
Car-focused navigation services are based on turns and distances of name...
Large volumes of interaction logs can be collected from NLP systems that...
Neural approaches to learning term embeddings have led to improved
compu...
Direct speech translation describes a scenario where only speech inputs ...
Interest in stochastic zeroth-order (SZO) methods has recently been revi...
Sequence-to-sequence learning involves a trade-off between signal streng...
We present a corpus of sentence-aligned triples of German audio, German ...
Sepsis is the leading cause of death in non-coronary intensive care unit...
We present Joey NMT, a minimalist neural machine translation toolkit bas...
Not all types of supervision signals are created equal: Different types ...
In many machine learning scenarios, supervision by gold labels is not
av...
We propose an interactive-predictive neural machine translation framewor...
In semantic parsing for question-answering, it is often too expensive to...
Stochastic zeroth-order (SZO), or gradient-free, optimization allows to
...
We present a study on reinforcement learning (RL) from human bandit feed...
We present an approach to interactive-predictive neural machine translat...
Counterfactual learning from human bandit feedback describes a scenario ...
We present the first real-world application of methods for improving neu...
The advantages of neural machine translation (NMT) have been extensively...
Counterfactual learning is a natural scenario to improve web-based machi...
The goal of counterfactual learning for statistical machine translation ...
We introduce and describe the results of a novel shared task on bandit
l...
Bandit structured prediction describes a stochastic optimization framewo...
Stochastic structured prediction under bandit feedback follows a learnin...
We present an approach to structured prediction from bandit feedback, ca...
We present an approach to improve statistical machine translation of ima...
We present a technique for automatic induction of slot annotations for
s...