Search Results for author:
Found 32 papers, 9 papers with code
Bandits Don’t Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits
Training data for machine translation (MT) is often sourced from a multitude of large corpora that are multi-faceted in nature, e. g. containing contents from multiple domains or different levels of quality or complexity.
Controlling Machine Translation for Multiple Attributes with Additive Interventions
Fine-grained control of machine translation (MT) outputs along multiple attributes is critical for many modern MT applications and is a requirement for gaining users’ trust.
Don’t Search for a Search Method — Simple Heuristics Suffice for Adversarial Text Attacks
Recently more attention has been given to adversarial attacks on neural networks for natural language processing (NLP).
Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts
We present an imitation learning approach where a teacher NMT system corrects the errors of an AST student without relying on manual transcripts.
Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets
Increasingly larger datasets have become a standard ingredient to advancing the state-of-the-art in NLP.
Large Raw Emotional Dataset with Aggregation Mechanism
We present a new data set for speech emotion recognition (SER) tasks called Dusha.
Ranked #1 on
Speech Emotion Recognition
on Dusha Podcast
Scaling Up Influence Functions
We address efficient calculation of influence functions for tracking predictions back to the training data.
Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits
Training data for machine translation (MT) is often sourced from a multitude of large corpora that are multi-faceted in nature, e. g. containing contents from multiple domains or different levels of quality or complexity.
Don't Search for a Search Method -- Simple Heuristics Suffice for Adversarial Text Attacks
Recently more attention has been given to adversarial attacks on neural networks for natural language processing (NLP).
Fixing exposure bias with imitation learning needs powerful oracles
We apply imitation learning (IL) to tackle the NMT exposure bias problem with error-correcting oracles, and evaluate an SMT lattice-based oracle which, despite its excellent performance in an unconstrained oracle translation task, turned out to be too pruned and idiosyncratic to serve as the oracle for IL.
MITI Minimum Information guidelines for highly multiplexed tissue images
The imminent release of tissue atlases combining multi-channel microscopy with single cell sequencing and other omics data from normal and diseased specimens creates an urgent need for data and metadata standards that guide data deposition, curation and release.
On the Impact of Word Error Rate on Acoustic-Linguistic Speech Emotion Recognition: An Update for the Deep Learning Era
Text encodings from automatic speech recognition (ASR) transcripts and audio representations have shown promise in speech emotion recognition (SER) ever since.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Real-time Streaming Wave-U-Net with Temporal Convolutions for Multichannel Speech Enhancement
In this paper, we describe the work that we have done to participate in Task1 of the ConferencingSpeech2021 challenge.
Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets
With the success of large-scale pre-training and multilingual modeling in Natural Language Processing (NLP), recent years have seen a proliferation of large, web-mined text datasets covering hundreds of languages.
Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization
Interest in stochastic zeroth-order (SZO) methods has recently been revived in black-box optimization scenarios such as adversarial black-box attacks to deep neural networks.
Learning to Segment Inputs for NMT Favors Character-Level Processing
Most modern neural machine translation (NMT) systems rely on presegmented inputs.
Sparse Stochastic Zeroth-Order Optimization with an Application to Bandit Structured Prediction
Stochastic zeroth-order (SZO), or gradient-free, optimization allows to optimize arbitrary functions by relying only on function evaluations under parameter perturbations, however, the iteration complexity of SZO methods suffers a factor proportional to the dimensionality of the perturbed function.
Sockeye: A Toolkit for Neural Machine Translation
Written in Python and built on MXNet, the toolkit offers scalable training and inference for the three most prominent encoder-decoder architectures: attentional recurrent neural networks, self-attentional transformers, and fully convolutional networks.
Counterfactual Learning from Bandit Feedback under Deterministic Logging : A Case Study in Statistical Machine Translation
The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system.
Counterfactual Learning from Bandit Feedback under Deterministic Logging: A Case Study in Statistical Machine Translation
The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system.
A Shared Task on Bandit Learning for Machine Translation
We introduce and describe the results of a novel shared task on bandit learning for machine translation.
Bandit Structured Prediction for Neural Sequence-to-Sequence Learning
Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback.
Stochastic Structured Prediction under Bandit Feedback
Stochastic structured prediction under bandit feedback follows a learning protocol where on each of a sequence of iterations, the learner receives an input, predicts an output structure, and receives partial feedback in form of a task loss evaluation of the predicted structure.
Bandit Structured Prediction for Learning from Partial Feedback in Statistical Machine Translation
We present an application to discriminative reranking in Statistical Machine Translation (SMT) where the learning algorithm only has access to a 1-BLEU loss evaluation of a predicted translation instead of obtaining a gold standard reference translation.
