Related papers: Reinforced Curriculum Learning on Pre-trained Neur…
Improving machine translation (MT) systems with translation memories (TMs) is of great interest to practitioners in the MT community. However, previous approaches require either a significant update of the model architecture and/or…
We propose a neural machine translation (NMT) approach that, instead of pursuing adequacy and fluency ("human-oriented" quality criteria), aims to generate translations that are best suited as input to a natural language processing…
Curriculum learning has been successfully used in reinforcement learning to accelerate the learning process, through knowledge transfer between tasks of increasing complexity. Critical tasks, in which suboptimal exploratory actions must be…
This study explores a learning-based tri-finger robotic arm manipulating task, which requires complex movements and coordination among the fingers. By employing reinforcement learning, we train an agent to acquire the necessary skills for…
Non-autoregressive (NAR) language models are known for their low latency in neural machine translation (NMT). However, a performance gap exists between NAR and autoregressive models due to the large decoding space and difficulty in…
Machine Translation (MT) has been widely used for cross-lingual classification, either by translating the test set into English and running inference with a monolingual model (translate-test), or translating the training set into the target…
Graph pre-training strategies have been attracting a surge of attention in the graph mining community, due to their flexibility in parameterizing graph neural networks (GNNs) without any label information. The key idea lies in encoding…
We present a survey on multilingual neural machine translation (MNMT), which has gained a lot of traction in the recent years. MNMT has been useful in improving translation quality as a result of knowledge transfer. MNMT is more promising…
Learning a well-informed heuristic function for hard task planning domains is an elusive problem. Although there are known neural network architectures to represent such heuristic knowledge, it is not obvious what concrete information is…
Multilingual Neural Machine Translation approaches are based on the use of task-specific models and the addition of one more language can only be done by retraining the whole system. In this work, we propose a new training schedule that…
The basic concept in Neural Machine Translation (NMT) is to train a large Neural Network that maximizes the translation performance on a given parallel corpus. NMT is then using a simple left-to-right beam-search decoder to generate new…
Neural Machine Translation (NMT) is the task of translating a text from one language to another with the use of a trained neural network. Several existing works aim at incorporating external information into NMT models to improve or control…
Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performance in unconstrained cases, it is non-trivial to impose…
While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector…
Recently, neural machine translation (NMT) has been extended to multilinguality, that is to handle more than one translation direction with a single system. Multilingual NMT showed competitive performance against pure bilingual systems.…
Recent progress in neural machine translation is directed towards larger neural networks trained on an increasing amount of hardware resources. As a result, NMT models are costly to train, both financially, due to the electricity and…
Intelligent selection of training data has proven a successful technique to simultaneously increase training efficiency and translation performance for phrase-based machine translation (PBMT). With the recent increase in popularity of…
Curriculum reinforcement learning (CRL) allows solving complex tasks by generating a tailored sequence of learning tasks, starting from easy ones and subsequently increasing their difficulty. Although the potential of curricula in RL has…
We propose a method to transfer knowledge across neural machine translation (NMT) models by means of a shared dynamic vocabulary. Our approach allows to extend an initial model for a given language pair to cover new languages by adapting…
Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard training approach based on random data shuffling, without any…