相关论文: Reducing Gender Bias in Machine Translation throug…

Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages. Learning a single model can enhance the…

We introduce negative space learning machine translation (NSL-MT), a training method for underresourced languages, that augments limited parallel data with synthetically generated violations of the target language's grammar and explicitly…

Back translation (BT) is one of the most significant technologies in NMT research fields. Existing attempts on BT share a common characteristic: they employ either beam search or random sampling to generate synthetic data with a backward…

Is bias amplified when neural machine translation (NMT) models are optimized for speed and evaluated on generic test sets using BLEU? We investigate architectures and techniques commonly used to speed up decoding in Transformer-based…

Existing studies addressing gender bias of pre-trained language models, usually build a small gender-neutral data set and conduct a second phase pre-training on the model with such data. However, given the limited size and concentrated…

Neural Machine translation is a challenging task due to the inherent complex nature and the fluidity that natural languages bring. Nonetheless, in recent years, it has achieved state-of-the-art performance in several language pairs.…

While neural machine translation (NMT) has achieved state-of-the-art translation performance, it is unable to capture the alignment between the input and output during the translation process. The lack of alignment in NMT models leads to…

Zero-shot cross-lingual knowledge transfer enables a multilingual pretrained language model, finetuned on a task in one language, make predictions for this task in other languages. While being broadly studied for natural language…

Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies. This paper shows effective techniques to transfer a…

Numerous studies have demonstrated the ability of neural language models to learn various linguistic properties without direct supervision. This work takes an initial step towards exploring the less researched topic of how neural models…

As the demand for inclusive language increases, concern has grown over the susceptibility of machine translation (MT) systems to reinforce gender stereotypes. This study investigates gender bias in two commercial MT systems, Google…

While synthetic bilingual corpora have demonstrated their effectiveness in low-resource neural machine translation (NMT), adding more synthetic data often deteriorates translation performance. In this work, we propose alternated training…

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 WinoMTDE, a new gender bias evaluation test set designed to assess occupational stereotyping and underrepresentation in German machine translation (MT) systems. Building on the automatic evaluation method introduced by…

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

The quality of neural machine translation can be improved by leveraging additional monolingual resources to create synthetic training data. Source-side monolingual data can be (forward-)translated into the target language for self-training;…

Machine translation (MT) has benefited from using synthetic training data originating from translating monolingual corpora, a technique known as backtranslation. Combining backtranslated data from different sources has led to better results…

Neural Machine Translation (NMT) has become the new state-of-the-art in several language pairs. However, it remains a challenging problem how to integrate NMT with a bilingual dictionary which mainly contains words rarely or never seen in…

Improving neural machine translation (NMT) models using the back-translations of the monolingual target data (synthetic parallel data) is currently the state-of-the-art approach for training improved translation systems. The quality of the…

We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original inputs to reconstructed…