Related papers: Viewing Knowledge Transfer in Multilingual Machine…

We study the problem of representation transfer in offline Reinforcement Learning (RL), where a learner has access to episodic data from a number of source tasks collected a priori, and aims to learn a shared representation to be used in…

Multilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. Despite being conceptually attractive, it often suffers from low output quality.…

The many-to-many multilingual neural machine translation can translate between language pairs unseen during training, i.e., zero-shot translation. Improving zero-shot translation requires the model to learn universal representations and…

Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. However, MTL must deal with challenges such as: overfitting to low resource tasks, catastrophic forgetting, and…

Cross-lingual transfer in natural language processing (NLP) models enhances multilingual performance by leveraging shared linguistic knowledge. However, traditional methods that process all data simultaneously often fail to mimic real-world…

The field of prosody transfer in speech synthesis systems is rapidly advancing. This research is focused on evaluating learning methods for adapting pre-trained monolingual text-to-speech (TTS) models to multilingual conditions, i.e.,…

Despite the recent popularity of Large Language Models (LLMs) in Machine Translation (MT), their performance in low-resource languages (LRLs) still lags significantly behind Neural Machine Translation (NMT) models. In this work, we explore…

Modern neural translation models based on the Transformer architecture are known for their high performance, particularly when trained on high-resource datasets. A standard next-token prediction training strategy, while widely adopted in…

Being able to rank the similarity of short text segments is an interesting bonus feature of neural machine translation. Translation-based similarity measures include direct and pivot translation probability, as well as translation…

Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning -- a key tool for performing meta-learning -- learns a…

Multilingual translation supports multiple translation directions by projecting all languages in a shared space, but the translation quality is undermined by the difference between languages in the text-only modality, especially when the…

Understanding representation transfer in multilingual neural machine translation (MNMT) can reveal the reason for the zero-shot translation deficiency. In this work, we systematically analyze the representational issue of MNMT models. We…

Autoregressive pretraining has become the de facto paradigm for learning general-purpose representations in large language models (LLMs). However, linear probe performance across downstream perception tasks shows substantial variability,…

Machine translation (MT) is an important task in natural language processing (NLP) as it automates the translation process and reduces the reliance on human translators. With the resurgence of neural networks, the translation quality…

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…

Pretraining and multitask learning are widely used to improve the speech to text translation performance. In this study, we are interested in training a speech to text translation model along with an auxiliary text to text translation task.…

Both human and machine translation play a central role in cross-lingual transfer learning: many multilingual datasets have been created through professional translation services, and using machine translation to translate either the test…

Large language models (LLMs) have achieved strong performance in general machine translation, yet their ability in culture-aware scenarios remains poorly understood. To bridge this gap, we introduce CanMT, a Culture-Aware Novel-Driven…

In this paper, we use the framework of neural machine translation to learn joint sentence representations across six very different languages. Our aim is that a representation which is independent of the language, is likely to capture the…

Current Machine Translation systems achieve very good results on a growing variety of language pairs and data sets. However, it is now well known that they produce fluent translation outputs that often can contain important meaning errors.…