Related papers: Multilingual Bidirectional Unsupervised Translatio…
Over the last few years two promising research directions in low-resource neural machine translation (NMT) have emerged. The first focuses on utilizing high-resource languages to improve the quality of low-resource languages via…
This paper considers the unsupervised domain adaptation problem for neural machine translation (NMT), where we assume the access to only monolingual text in either the source or target language in the new domain. We propose a cross-lingual…
Most translation tasks among languages belong to the zero-resource translation problem where parallel corpora are unavailable. Multilingual neural machine translation (MNMT) enables one-pass translation using shared semantic space for all…
While achieving state-of-the-art results in multiple tasks and languages, translation-based cross-lingual transfer is often overlooked in favour of massively multilingual pre-trained encoders. Arguably, this is due to its main limitations:…
Pre-training has proven to be effective in unsupervised machine translation due to its ability to model deep context information in cross-lingual scenarios. However, the cross-lingual information obtained from shared BPE spaces is…
Neural machine translation (NMT) has recently achieved impressive results. A potential problem of the existing NMT algorithm, however, is that the decoding is conducted from left to right, without considering the right context. This paper…
Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo…
Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between…
Zero-shot neural machine translation is an attractive goal because of the high cost of obtaining data and building translation systems for new translation directions. However, previous papers have reported mixed success in zero-shot…
Scaling multilingual representation learning beyond the hundred most frequent languages is challenging, in particular to cover the long tail of low-resource languages. A promising approach has been to train one-for-all multilingual models…
While end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains. In this paper, we propose a method for zero-resource NMT…
In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training. The proposed approach consists of two stages. In the first…
Recent advances in statistical machine translation via the adoption of neural sequence-to-sequence models empower the end-to-end system to achieve state-of-the-art in many WMT benchmarks. The performance of such machine translation (MT)…
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,…
In this paper, we propose a novel finetuning algorithm for the recently introduced multi-way, mulitlingual neural machine translate that enables zero-resource machine translation. When used together with novel many-to-one translation…
We present a probabilistic framework for multilingual neural machine translation that encompasses supervised and unsupervised setups, focusing on unsupervised translation. In addition to studying the vanilla case where there is only…
This paper studies the practicality of the current state-of-the-art unsupervised methods in neural machine translation (NMT). In ten translation tasks with various data settings, we analyze the conditions under which the unsupervised…
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,…
Large multilingual language models such as mBERT or XLM-R enable zero-shot cross-lingual transfer in various IR and NLP tasks. Cao et al. (2020) proposed a data- and compute-efficient method for cross-lingual adjustment of mBERT that uses a…
Multi-source translation is an approach to exploit multiple inputs (e.g. in two different languages) to increase translation accuracy. In this paper, we examine approaches for multi-source neural machine translation (NMT) using an…