Related papers: EBBS: An Ensemble with Bi-Level Beam Search for Ze…
Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zeroshot) translation directions not observed at training time. We…
Zero-shot neural machine translation is an attractive goal because of the high cost of obtaining data and building translation systems for new translation directions. However, previous papers have reported mixed success in zero-shot…
Recent advancements in NLP have resulted in models with specialized strengths, such as processing multimodal inputs or excelling in specific domains. However, real-world tasks, like multimodal translation, often require a combination of…
Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training…
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…
Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that…
Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the…
Generalization and reliability of multilingual translation often highly depend on the amount of available parallel data for each language pair of interest. In this paper, we focus on zero-shot generalization---a challenging setup that tests…
In this paper, we proposed two strategies which can be applied to a multilingual neural machine translation system in order to better tackle zero-shot scenarios despite not having any parallel corpus. The experiments show that they are…
Multilingual Neural Machine Translation (NMT) models are capable of translating between multiple source and target languages. Despite various approaches to train such models, they have difficulty with zero-shot translation: translating…
Multilingual neural machine translation systems learn to map sentences of different languages into a common representation space. Intuitively, with a growing number of seen languages the encoder sentence representation grows more flexible…
Neural Machine Translation (NMT) approaches employing monolingual data are showing steady improvements in resource rich conditions. However, evaluations using real-world low-resource languages still result in unsatisfactory performance.…
Neural Machine Translation (NMT) systems rely on large amounts of parallel data. This is a major challenge for low-resource languages. Building on recent work on unsupervised and semi-supervised methods, we present an approach that combines…
Despite the recent remarkable advances in neural machine translation, translation quality for low-resource language pairs remains subpar. Ensembling multiple systems is a widely adopted technique to enhance performance, often accomplished…
Multilingual neural machine translation can translate unseen language pairs during training, i.e. zero-shot translation. However, the zero-shot translation is always unstable. Although prior works attributed the instability to the…
An important concern in training multilingual neural machine translation (NMT) is to translate between language pairs unseen during training, i.e zero-shot translation. Improving this ability kills two birds with one stone by providing an…
We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models. Our method consists of three steps: few-shot amplification, distillation, and backtranslation. We first…
Speech Translation (ST) is the task of translating speech in one language into text in another language. Traditional cascaded approaches for ST, using Automatic Speech Recognition (ASR) and Machine Translation (MT) systems, are prone to…
We introduce the task of zero-shot style transfer between different languages. Our training data includes multilingual parallel corpora, but does not contain any parallel sentences between styles, similarly to the recent previous work. We…