Related papers: A Multilingual View of Unsupervised Machine Transl…

We introduce Generative Neural Machine Translation (GNMT), a latent variable architecture which is designed to model the semantics of the source and target sentences. We modify an encoder-decoder translation model by adding a latent…

In this paper, we propose two new features for estimating phrase-based machine translation parameters from mainly monolingual data. Our method is based on two recently introduced neural network vector representation models for words and…

Supervised learning in Neural Machine Translation (NMT) typically follows a teacher forcing paradigm where reference tokens constitute the conditioning context in the model's prediction, instead of its own previous predictions. In order to…

The performance of neural machine translation systems is commonly evaluated in terms of BLEU. However, due to its reliance on target language properties and generation, the BLEU metric does not allow an assessment of which translation…

We present a survey on multilingual neural machine translation (MNMT), which has gained a lot of traction in the recent years. MNMT has been useful in improving translation quality as a result of knowledge transfer. MNMT is more promising…

Sequence-to-sequence neural translation models learn semantic and syntactic relations between sentence pairs by optimizing the likelihood of the target given the source, i.e., $p(y|x)$, an objective that ignores other potentially useful…

Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite…

In this paper, we propose a new paradigm for paraphrase generation by treating the task as unsupervised machine translation (UMT) based on the assumption that there must be pairs of sentences expressing the same meaning in a large-scale…

We present a generic framework for data augmentation via dependency subtree swapping that is applicable to machine translation. We extract corresponding subtrees from the dependency parse trees of the source and target sentences and swap…

This work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a seq2seq model are initialized with the pretrained weights…

We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data. One popular strategy is to reduce multilingual alignment to the much simplified…

Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, naive training for…

Multimodal machine translation (MMT) aims to improve translation quality by incorporating information from other modalities, such as vision. Previous MMT systems mainly focus on better access and use of visual information and tend to…

Successful methods for unsupervised neural machine translation (UNMT) employ crosslingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the model to align the…

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…

We propose a simple method to align multilingual contextual embeddings as a post-pretraining step for improved zero-shot cross-lingual transferability of the pretrained models. Using parallel data, our method aligns embeddings on the word…

The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a single model. Its improved translation performance on low…

Multilingual machine translation (MMT) benefits from cross-lingual transfer but is a challenging multitask optimization problem. This is partly because there is no clear framework to systematically learn language-specific parameters.…

This work focuses on comparing different solutions for machine translation on low resource language pairs, namely, with zero-shot transfer learning and unsupervised machine translation. We discuss how the data size affects the performance…

Variational Neural Machine Translation (VNMT) is an attractive framework for modeling the generation of target translations, conditioned not only on the source sentence but also on some latent random variables. The latent variable modeling…