Related papers: Understanding and Mitigating the Uncertainty in Ze…
Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper, we propose two simple…
The capacity and effectiveness of pre-trained multilingual models (MLMs) for zero-shot cross-lingual transfer is well established. However, phenomena of positive or negative transfer, and the effect of language choice still need to be fully…
Back-translation is a critical component of Unsupervised Neural Machine Translation (UNMT), which generates pseudo parallel data from target monolingual data. A UNMT model is trained on the pseudo parallel data with translated source, and…
A new paradigm for machine translation has recently emerged: fine-tuning large language models (LLM) on parallel text has been shown to outperform dedicated translation systems trained in a supervised fashion on much larger amounts of…
Several neural-based metrics have been recently proposed to evaluate machine translation quality. However, all of them resort to point estimates, which provide limited information at segment level. This is made worse as they are trained on…
Neural networks have demonstrated significant advancements in Neural Machine Translation (NMT) compared to conventional phrase-based approaches. However, Multilingual Neural Machine Translation (MNMT) in extremely low-resource settings…
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…
Efficient utilisation of both intra- and extra-textual context remains one of the critical gaps between machine and human translation. Existing research has primarily focused on providing individual, well-defined types of context in…
While it has been shown that Neural Machine Translation (NMT) is highly sensitive to noisy parallel training samples, prior work treats all types of mismatches between source and target as noise. As a result, it remains unclear how samples…
We explore the transferability of a multilingual neural machine translation model to unseen languages when the transfer is grounded solely on the cross-lingual word embeddings. Our experimental results show that the translation knowledge…
Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…
Recent research has shown that independently trained encoders and decoders, combined through a shared fixed-size representation, can achieve competitive performance in speech-to-text translation. In this work, we show that this type of…
This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextualized multilingual multimodal embeddings.…
Neural machine translation (NMT) has significantly improved the quality of automatic translation models. One of the main challenges in current systems is the translation of rare words. We present a generic approach to address this weakness…
Through the development of neural machine translation, the quality of machine translation systems has been improved significantly. By exploiting advancements in deep learning, systems are now able to better approximate the complex mapping…
Recent years have witnessed the rapid advance in neural machine translation (NMT), the core of which lies in the encoder-decoder architecture. Inspired by the recent progress of large-scale pre-trained language models on machine translation…
Self-training has proven effective for improving NMT performance by augmenting model training with synthetic parallel data. The common practice is to construct synthetic data based on a randomly sampled subset of large-scale monolingual…
Neural machine translation (NMT) models often suffer from gender biases that harm users and society at large. In this work, we explore how bridging the gap between languages for which parallel data is not available affects gender bias in…
Pretrained multilingual models are able to perform cross-lingual transfer in a zero-shot setting, even for languages unseen during pretraining. However, prior work evaluating performance on unseen languages has largely been limited to…
This paper describes our submission of the WMT 2020 Shared Task on Sentence Level Direct Assessment, Quality Estimation (QE). In this study, we empirically reveal the \textit{mismatching issue} when directly adopting BERTScore to QE.…