Related papers: It is Not as Good as You Think! Evaluating Simulta…
We introduce a dataset comprising commercial machine translations, gathered weekly over six years across 12 translation directions. Since human A/B testing is commonly used, we assume commercial systems improve over time, which enables us…
Machine translation (MT) systems are now able to provide very accurate results for high resource language pairs. However, for many low resource languages, MT is still under active research. In this paper, we develop and share a dataset to…
Simultaneous machine translation has recently gained traction thanks to significant quality improvements and the advent of streaming applications. Simultaneous translation systems need to find a trade-off between translation quality and…
Neural machine translation systems require large amounts of training data and resources. Even with this, the quality of the translations may be insufficient for some users or domains. In such cases, the output of the system must be revised…
End-to-end In-Image Machine Translation (IIMT) aims to convert text embedded within an image into a target language while preserving the original visual context, layout, and rendering style. However, existing IIMT benchmarks are largely…
We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of…
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.…
Even with the latest developments in deep learning and large-scale language modeling, the task of machine translation (MT) of low-resource languages remains a challenge. Neural MT systems can be trained in an unsupervised way without any…
The encoder-decoder framework for neural machine translation (NMT) has been shown effective in large data scenarios, but is much less effective for low-resource languages. We present a transfer learning method that significantly improves…
Simultaneous machine translation (SimulMT) presents a challenging trade-off between translation quality and latency. Recent studies have shown that LLMs can achieve good performance in SimulMT tasks. However, this often comes at the expense…
The translation of pronouns presents a special challenge to machine translation to this day, since it often requires context outside the current sentence. Recent work on models that have access to information across sentence boundaries has…
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,…
Multilingual machine translation (MT) benchmarks play a central role in evaluating the capabilities of modern MT systems. Among them, the FLORES+ benchmark is widely used, offering English-to-many translation data for over 200 languages,…
Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training. Consequently, techniques for augmenting the training set have become popular recently. One of these methods is…
We propose the on-the-fly ensembling of a machine translation model with an LLM, prompted on the same task and input. We perform experiments on 4 language pairs (both directions) with varying data amounts. We find that a slightly…
This paper describes the University of Sydney's submission of the WMT 2019 shared news translation task. We participated in the Finnish$\rightarrow$English direction and got the best BLEU(33.0) score among all the participants. Our system…
Neural machine translation (NMT) models are conventionally trained with token-level negative log-likelihood (NLL), which does not guarantee that the generated translations will be optimized for a selected sequence-level evaluation metric.…
An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. This work broadens the understanding of back-translation and…
Given the rise of a new approach to MT, Neural MT (NMT), and its promising performance on different text types, we assess the translation quality it can attain on what is perceived to be the greatest challenge for MT: literary text.…
We investigate different approaches to translate between similar languages under low resource conditions, as part of our contribution to the WMT 2020 Similar Languages Translation Shared Task. We submitted Transformer-based bilingual and…