Search Results for author:
Found 26 papers, 3 papers with code
The AFRL WMT20 News Translation Systems
This report summarizes the Air Force Research Laboratory (AFRL) machine translation (MT) systems submitted to the news-translation task as part of the 2020 Conference on Machine Translation (WMT20) evaluation campaign.
Tune in: The AFRL WMT21 News-Translation Systems
This paper describes the Air Force Research Laboratory (AFRL) machine translation sys- tems and the improvements that were developed during the WMT21 evaluation campaign.
The MITLL-AFRL IWSLT 2016 Systems
This report summarizes the MITLL-AFRL MT and ASR systems and the experiments run during the 2016 IWSLT evaluation campaign.
The AFRL IWSLT 2018 Systems: What Worked, What Didn’t
This report summarizes the Air Force Research Laboratory (AFRL) machine translation (MT) and automatic speech recognition (ASR) systems submitted to the spoken language translation (SLT) and low-resource MT tasks as part of the IWSLT18 evaluation campaign.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
The Case for Evaluating Multimodal Translation Models on Text Datasets
Therefore, we propose that MMT models be evaluated using 1) the CoMMuTE evaluation framework, which measures the use of visual information by MMT models, 2) the text-only WMT news translation task test sets, which evaluates translation performance against complex sentences, and 3) the Multi30k test sets, for measuring MMT model performance against a real MMT dataset.
Adding Multimodal Capabilities to a Text-only Translation Model
While most current work in multimodal machine translation (MMT) uses the Multi30k dataset for training and evaluation, we find that the resulting models overfit to the Multi30k dataset to an extreme degree.
Detecting Concrete Visual Tokens for Multimodal Machine Translation
The challenge of visual grounding and masking in multimodal machine translation (MMT) systems has encouraged varying approaches to the detection and selection of visually-grounded text tokens for masking.
A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine Translation
Large language models such as BERT and the GPT series started a paradigm shift that calls for building general-purpose models via pre-training on large datasets, followed by fine-tuning on task-specific datasets.
Learning When to Say "I Don't Know"
We propose a new Reject Option Classification technique to identify and remove regions of uncertainty in the decision space for a given neural classifier and dataset.
The AFRL IWSLT 2020 Systems: Work-From-Home Edition
This report summarizes the Air Force Research Laboratory (AFRL) submission to the offline spoken language translation (SLT) task as part of the IWSLT 2020 evaluation campaign.
The AFRL WMT19 Systems: Old Favorites and New Tricks
This paper describes the Air Force Research Laboratory (AFRL) machine translation systems and the improvements that were developed during the WMT19 evaluation campaign.
Quality and Coverage: The AFRL Submission to the WMT19 Parallel Corpus Filtering for Low-Resource Conditions Task
The WMT19 Parallel Corpus Filtering For Low-Resource Conditions Task aims to test various methods of filtering a noisy parallel corpora, to make them useful for training machine translation systems.
Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation
Continued training is an effective method for domain adaptation in neural machine translation.
An Empirical Exploration of Curriculum Learning for Neural Machine Translation
Machine translation systems based on deep neural networks are expensive to train.
The AFRL WMT18 Systems: Ensembling, Continuation and Combination
This paper describes the Air Force Research Laboratory (AFRL) machine translation systems and the improvements that were developed during the WMT18 evaluation campaign.
Coverage and Cynicism: The AFRL Submission to the WMT 2018 Parallel Corpus Filtering Task
The WMT 2018 Parallel Corpus Filtering Task aims to test various methods of filtering a noisy parallel corpus, to make it useful for training machine translation systems.
The AFRL-Ohio State WMT18 Multimodal System: Combining Visual with Traditional
AFRL-Ohio State extends its usage of visual domain-driven machine translation for use as a peer with traditional machine translation systems.
Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation
To better understand the effectiveness of continued training, we analyze the major components of a neural machine translation system (the encoder, decoder, and each embedding space) and consider each component's contribution to, and capacity for, domain adaptation.
