Related papers: Multi-Task Cross-Lingual Sequence Tagging from Scr…

Parallel deep learning architectures like fine-tuned BERT and MT-DNN, have quickly become the state of the art, bypassing previous deep and shallow learning methods by a large margin. More recently, pre-trained models from large related…

The research addresses sensor task management for radar systems, focusing on efficiently searching and tracking multiple targets using reinforcement learning. The approach develops a 3D simulation environment with an active electronically…

The development of neural networks and pretraining techniques has spawned many sentence-level tagging systems that achieved superior performance on typical benchmarks. However, a relatively less discussed topic is what if more context…

Algorithmic image-based diagnosis and prognosis of neurodegenerative diseases on longitudinal data has drawn great interest from computer vision researchers. The current state-of-the-art models for many image classification tasks are based…

Cross-lingual transfer learning is an invaluable tool for overcoming data scarcity, yet selecting a suitable transfer language remains a challenge. The precise roles of linguistic typology, training data, and model architecture in transfer…

Recent advances in conditional recurrent language modelling have mainly focused on network architectures (e.g., attention mechanism), learning algorithms (e.g., scheduled sampling and sequence-level training) and novel applications (e.g.,…

Automated analysis methods are crucial aids for monitoring and defending a network to protect the sensitive or confidential data it hosts. This work introduces a flexible, powerful, and unsupervised approach to detecting anomalous behavior…

We present a new recurrent neural network topology to enhance state-of-the-art machine learning systems by incorporating a broader context. Our approach overcomes recent limitations with extended narratives through a multi-layered…

In order to achieve deep natural language understanding, syntactic constituent parsing is a vital step, highly demanded by many artificial intelligence systems to process both text and speech. One of the most recent proposals is the use of…

Recurrent neural networks (RNNs) have reached striking performance in many natural language processing tasks. This has renewed interest in whether these generic sequence processing devices are inducing genuine linguistic knowledge. Nearly…

Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…

Recurrent Neural Networks (RNNs) have been widely used in processing natural language tasks and achieve huge success. Traditional RNNs usually treat each token in a sentence uniformly and equally. However, this may miss the rich semantic…

In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information…

A key attribute that drives the unprecedented success of modern Recurrent Neural Networks (RNNs) on learning tasks which involve sequential data, is their ability to model intricate long-term temporal dependencies. However, a well…

We introduce DsDs: a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision, and realistically scales to hundreds of low-resource languages. The model exploits annotation projection, instance…

Learning algorithms for natural language processing (NLP) tasks traditionally rely on manually defined relevant contextual features. On the other hand, neural network models using an only distributional representation of words have been…

Multilingual models jointly pretrained on multiple languages have achieved remarkable performance on various multilingual downstream tasks. Moreover, models finetuned on a single monolingual downstream task have shown to generalize to…

Language recognition system is typically trained directly to optimize classification error on the target language labels, without using the external, or meta-information in the estimation of the model parameters. However labels are not…

To solve the Grammatical Error Correction (GEC) problem , a mapping between a source sequence and a target one is needed, where the two differ only on few spans. For this reason, the attention has been shifted to the non-autoregressive or…

Neural language models (LMs) are typically trained using only lexical features, such as surface forms of words. In this paper, we argue this deprives the LM of crucial syntactic signals that can be detected at high confidence using existing…