Search Results for author:
Found 65 papers, 20 papers with code
Self-Regulated Interactive Sequence-to-Sequence Learning
Not all types of supervision signals are created equal: Different types of feedback have different costs and effects on learning.
Joey NMT: A Minimalist NMT Toolkit for Novices
We present Joey NMT, a minimalist neural machine translation toolkit based on PyTorch that is specifically designed for novices.
JoeyS2T: Minimalistic Speech-to-Text Modeling with JoeyNMT
JoeyS2T is a JoeyNMT extension for speech-to-text tasks such as automatic speech recognition and end-to-end speech translation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas
Vision and language navigation (VLN) is a challenging visually-grounded language understanding task.
Ranked #1 on
Vision and Language Navigation
on map2seq
Text-to-OverpassQL: A Natural Language Interface for Complex Geodata Querying of OpenStreetMap
We present Text-to-OverpassQL, a task designed to facilitate a natural language interface for querying geodata from OpenStreetMap (OSM).
VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View
In this work, we propose VELMA, an embodied LLM agent that uses a verbalization of the trajectory and of visual environment observations as contextual prompt for the next action.
A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation
We present an approach to interactive-predictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial translations.
Ensembling Neural Networks for Improved Prediction and Privacy in Early Diagnosis of Sepsis
Ensembling neural networks is a long-standing technique for improving the generalization error of neural networks by combining networks with orthogonal properties via a committee decision.
LibriVoxDeEn: A Corpus for German-to-English Speech Translation and German Speech Recognition
An even larger dataset comprising 547 hours of German speech aligned to German text is available for speech recognition.
Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning
We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT).
Bandit Structured Prediction for Neural Sequence-to-Sequence Learning
Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback.
On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR
Our method, called Aligned Data Augmentation (ADA) for ASR, replaces transcribed tokens and the speech representations in an aligned manner to generate previously unseen training pairs.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
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.
Correct Me If You Can: Learning from Error Corrections and Markings
Sequence-to-sequence learning involves a trade-off between signal strength and annotation cost of training data.
Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback
Counterfactual learning from human bandit feedback describes a scenario where user feedback on the quality of outputs of a historic system is logged and used to improve a target system.
Counterfactual Learning from Human Proofreading Feedback for Semantic Parsing
In semantic parsing for question-answering, it is often too expensive to collect gold parses or even gold answers as supervision signals.
Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss
We show that bipolar ramp loss objectives outperform other non-bipolar ramp loss objectives and minimum risk training (MRT) on both weakly supervised tasks, as well as on a supervised machine translation task.
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.
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.
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.
Can Neural Machine Translation be Improved with User Feedback?
We present the first real-world application of methods for improving neural machine translation (NMT) with human reinforcement, based on explicit and implicit user feedback collected on the eBay e-commerce platform.
A User-Study on Online Adaptation of Neural Machine Translation to Human Post-Edits
The advantages of neural machine translation (NMT) have been extensively validated for offline translation of several language pairs for different domains of spoken and written language.
Counterfactual Learning for Machine Translation: Degeneracies and Solutions
Counterfactual learning is a natural scenario to improve web-based machine translation services by offline learning from feedback logged during user interactions.
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.
Multimodal Pivots for Image Caption Translation
We present an approach to improve statistical machine translation of image descriptions by multimodal pivots defined in visual space.
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.
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.
Learning to translate from graded and negative relevance information
We present an approach for learning to translate by exploiting cross-lingual link structure in multilingual document collections.
NLmaps: A Natural Language Interface to Query OpenStreetMap
We present a Natural Language Interface (nlmaps. cl. uni-heidelberg. de) to query OpenStreetMap.
A Post-editing Interface for Immediate Adaptation in Statistical Machine Translation
Our translation systems may learn from post-edits using several weight, language model and novel translation model adaptation techniques, in part by exploiting the output of the graphical interface.
Interactive-Predictive Neural Machine Translation through Reinforcement and Imitation
We propose an interactive-predictive neural machine translation framework for easier model personalization using reinforcement and imitation learning.
Leveraging Implicit Expert Knowledge for Non-Circular Machine Learning in Sepsis Prediction
Sepsis is the leading cause of death in non-coronary intensive care units.
Cascaded Models With Cyclic Feedback For Direct Speech Translation
Direct speech translation describes a scenario where only speech inputs and corresponding translations are available.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Embedding Meta-Textual Information for Improved Learning to Rank
Neural approaches to learning term embeddings have led to improved computation of similarity and ranking in information retrieval (IR).
Offline Reinforcement Learning from Human Feedback in Real-World Sequence-to-Sequence Tasks
Large volumes of interaction logs can be collected from NLP systems that are deployed in the real world.
Generating Landmark Navigation Instructions from Maps as a Graph-to-Text Problem
Car-focused navigation services are based on turns and distances of named streets, whereas navigation instructions naturally used by humans are centered around physical objects called landmarks.
Natural Language Landmark Navigation Instructions Generation
Error-Aware Interactive Semantic Parsing of OpenStreetMap
In semantic parsing of geographical queries against real-world databases such as OpenStreetMap (OSM), unique correct answers do not necessarily exist.
False perfection in machine prediction: Detecting and assessing circularity problems in machine learning
This paper is an excerpt of an early version of Chapter 2 of the book "Validity, Reliability, and Significance.
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).
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).
Multi-Task Modeling of Phonographic Languages: Translating Middle Egyptian Hieroglyphs
Machine translation of ancient languages faces a low-resource problem, caused by the limited amount of available textual source data and their translations.
Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translation
End-to-end speech translation relies on data that pair source-language speech inputs with corresponding translations into a target language.
Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and Translation
Data augmentation is a technique to generate new training data based on existing data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Towards Inferential Reproducibility of Machine Learning Research
Instead of removing noise, we propose to incorporate several sources of variance, including their interaction with data properties, into an analysis of significance and reliability of machine learning evaluation, with the aim to draw inferences beyond particular instances of trained models.
Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training
Supervised learning in Neural Machine Translation (NMT) typically follows a teacher forcing paradigm where reference tokens constitute the conditioning context in the model's prediction, instead of its own previous predictions.
Validity problems in clinical machine learning by indirect data labeling using consensus definitions
We demonstrate a validity problem of machine learning in the vital application area of disease diagnosis in medicine.
