Related papers: The Missing Ingredient in Zero-Shot Neural Machine…
Current Neural Machine Translation (NMT) employs a language-specific encoder to represent the source sentence and adopts a language-specific decoder to generate target translation. This language-dependent design leads to large-scale network…
We demonstrate the potential of few-shot translation systems, trained with unpaired language data, for both high and low-resource language pairs. We show that with only 5 examples of high-quality translation data shown at inference, a…
Conventional Neural Machine Translation (NMT) models benefit from the training with an additional agent, e.g., dual learning, and bidirectional decoding with one agent decoding from left to right and the other decoding in the opposite…
Neural Machine Translation (NMT) typically leverages monolingual data in training through backtranslation. We investigate an alternative simple method to use monolingual data for NMT training: We combine the scores of a pre-trained and…
The rapid advancement of Large Language Models (LLMs), particularly those trained on multilingual corpora, has intensified the need for a deeper understanding of their performance across a diverse range of languages and model sizes. Our…
In Neural Machine Translation (NMT) the usage of subwords and characters as source and target units offers a simple and flexible solution for translation of rare and unseen words. However, selecting the optimal subword segmentation involves…
Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e.g., document-level translation, or having meta-information. Although there exist various…
Existing multilingual neural machine translation (MNMT) approaches mainly focus on improving models with the encoder-decoder architecture to translate multiple languages. However, decoder-only architecture has been explored less in MNMT due…
We propose a new paradigm for zero-shot learners that is format agnostic, i.e., it is compatible with any format and applicable to a list of language tasks, such as text classification, commonsense reasoning, coreference resolution, and…
Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process. Despite…
Simultaneous translation involves translating a sentence before the speaker's utterance is completed in order to realize real-time understanding in multiple languages. This task is significantly more challenging than the general full…
Neural Networks trained with gradient descent are known to be susceptible to catastrophic forgetting caused by parameter shift during the training process. In the context of Neural Machine Translation (NMT) this results in poor performance…
We present a framework for machine translation evaluation using neural networks in a pairwise setting, where the goal is to select the better translation from a pair of hypotheses, given the reference translation. In this framework,…
Recent studies have shown remarkable success in unsupervised image-to-image translation. However, if there has no access to enough images in target classes, learning a mapping from source classes to the target classes always suffers from…
Modern neural machine translation (NMT) models have achieved competitive performance in standard benchmarks such as WMT. However, there still exist significant issues such as robustness, domain generalization, etc. In this paper, we study…
Pretrained multilingual models (PMMs) enable zero-shot learning via cross-lingual transfer, performing best for languages seen during pretraining. While methods exist to improve performance for unseen languages, they have almost exclusively…
Neural chat translation (NCT) aims to translate a cross-lingual chat between speakers of different languages. Existing context-aware NMT models cannot achieve satisfactory performances due to the following inherent problems: 1) limited…
Multilingual pretrained language models have demonstrated remarkable zero-shot cross-lingual transfer capabilities. Such transfer emerges by fine-tuning on a task of interest in one language and evaluating on a distinct language, not seen…
Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domain-specific projects. Machine translation (MT) has achieved…
Adapter layers are lightweight, learnable units inserted between transformer layers. Recent work explores using such layers for neural machine translation (NMT), to adapt pre-trained models to new domains or language pairs, training only a…