Related papers: Semi-Supervised Learning for Neural Machine Transl…
The increasing volume of scientific research necessitates effective communication across language barriers. Machine translation (MT) offers a promising solution for accessing international publications. However, the scientific domain…
We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of…
We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data. Our method connects autoencoding and neural machine translation to force the source and…
This paper demonstrates that multilingual pretraining and multilingual fine-tuning are both critical for facilitating cross-lingual transfer in zero-shot translation, where the neural machine translation (NMT) model is tested on source…
An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of the back-translations of the target-side monolingual data. The standard back-translation…
We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to…
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.…
Unsupervised neural machine translation (UNMT) requires only monolingual data of similar language pairs during training and can produce bi-directional translation models with relatively good performance on alphabetic languages (Lample et…
In the last few years, unpaired image-to-image translation has witnessed remarkable progress. Although the latest methods are able to generate realistic images, they crucially rely on a large number of labeled images. Recently, some methods…
Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of "easy" samples from training data at the early training stage. This is not always achievable for low-resource languages where…
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…
Multilingual neural machine translation (MNMT) trained in multiple language pairs has attracted considerable attention due to fewer model parameters and lower training costs by sharing knowledge among multiple languages. Nonetheless,…
Simultaneous machine translation (SiMT) is usually done via sequence-level knowledge distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model. However, there is still a significant performance gap between NMT and…
Unsupervised translation has reached impressive performance on resource-rich language pairs such as English-French and English-German. However, early studies have shown that in more realistic settings involving low-resource, rare languages,…
Most previous neural text-to-speech (TTS) methods are mainly based on supervised learning methods, which means they depend on a large training dataset and hard to achieve comparable performance under low-resource conditions. To address this…
This paper proposes a tool for efficiently constructing high-quality parallel corpora with minimizing human labor and making this tool publicly available. Our proposed construction process is based on neural machine translation (NMT) to…
In this paper, we propose an effective way for biasing the attention mechanism of a sequence-to-sequence neural machine translation (NMT) model towards the well-studied statistical word alignment models. We show that our novel guided…
Unsupervised representation learning algorithms such as word2vec and ELMo improve the accuracy of many supervised NLP models, mainly because they can take advantage of large amounts of unlabeled text. However, the supervised models only…
When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others. Standard practice is to up-sample…