Related papers: CUNI System for the WMT19 Robustness Task
The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic…
Character-based translation has several appealing advantages, but its performance is in general worse than a carefully tuned BPE baseline. In this paper we study the impact of character-based input and output with the Transformer…
Existing neural machine translation (NMT) studies mainly focus on developing dataset-specific models based on data from different tasks (e.g., document translation and chat translation). Although the dataset-specific models have achieved…
Transformer emerges as a powerful tool for visual recognition. In addition to demonstrating competitive performance on a broad range of visual benchmarks, recent works also argue that Transformers are much more robust than Convolutions…
Large language models have demonstrated exceptional performance across multiple crosslingual NLP tasks, including machine translation (MT). However, persistent challenges remain in addressing context-sensitive units (CSUs), such as…
This paper describes the submission of LMU Munich to the WMT 2020 unsupervised shared task, in two language directions, German<->Upper Sorbian. Our core unsupervised neural machine translation (UNMT) system follows the strategy of…
In a multiple-input multiple-output (MIMO) system, the availability of channel state information (CSI) at the transmitter is essential for performance improvement. Recent convolutional neural network (NN) based techniques show competitive…
Training deep neural network classifiers that are certifiably robust against adversarial attacks is critical to ensuring the security and reliability of AI-controlled systems. Although numerous state-of-the-art certified training methods…
Reinforcement learning has achieved significant milestones, but sample efficiency remains a bottleneck for real-world applications. Recently, CrossQ has demonstrated state-of-the-art sample efficiency with a low update-to-data (UTD) ratio…
The high-quality translation results produced by machine translation (MT) systems still pose a huge challenge for automatic evaluation. Current MT evaluation pays the same attention to each sentence component, while the questions of…
Reinforcement learning has achieved significant milestones, but sample efficiency remains a bottleneck for real-world applications. Recently, CrossQ has demonstrated state-of-the-art sample efficiency with a low update-to-data (UTD) ratio…
The application of quantum machine learning to large-scale high-resolution image datasets is not yet possible due to the limited number of qubits and relatively high level of noise in the current generation of quantum devices. In this work,…
Large Language Models (LLMs) consistently under perform in low-resource linguistic contexts such as Konkani. This performance deficit stems from acute training data scarcity compounded by high script diversity across Devanagari, Romi and…
Text generation models are notoriously vulnerable to errors in the training data. With the wide-spread availability of massive amounts of web-crawled data becoming more commonplace, how can we enhance the robustness of models trained on a…
Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on perturbed data…
The task of text classification using Bidirectional based LSTM architectures is computationally expensive and time consuming to train. For this, transformers were discovered which effectively give good performance as compared to the…
This paper describes SYSTRAN's systems submitted to the WMT 2017 shared news translation task for English-German, in both translation directions. Our systems are built using OpenNMT, an open-source neural machine translation system,…
Natural language inference (NLI) data has proven useful in benchmarking and, especially, as pretraining data for tasks requiring language understanding. However, the crowdsourcing protocol that was used to collect this data has known issues…
In this work, we propose an information theory based framework DeepMI to train deep neural networks (DNN) using Mutual Information (MI). The DeepMI framework is especially targeted but not limited to the learning of real world tasks in an…
Noisy training data can significantly degrade the performance of language-model-based classifiers, particularly in non-topical classification tasks. In this study we designed a methodological framework to assess the impact of denoising.…