Related papers: PEACH: Pre-Training Sequence-to-Sequence Multiling…
This research article examines the effectiveness of various pretraining strategies for developing machine translation models tailored to low-resource languages. Although this work considers several low-resource languages, including…
Even with the latest developments in deep learning and large-scale language modeling, the task of machine translation (MT) of low-resource languages remains a challenge. Neural MT systems can be trained in an unsupervised way without any…
Semi-supervised learning through deep generative models and multi-lingual pretraining techniques have orchestrated tremendous success across different areas of NLP. Nonetheless, their development has happened in isolation, while the…
Monolingual data have been demonstrated to be helpful in improving translation quality of both statistical machine translation (SMT) systems and neural machine translation (NMT) systems, especially in resource-poor or domain adaptation…
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…
Neural text-to-speech (TTS) models can synthesize natural human speech when trained on large amounts of transcribed speech. However, collecting such large-scale transcribed data is expensive. This paper proposes an unsupervised pre-training…
Achieving universal translation between all human language pairs is the holy-grail of machine translation (MT) research. While recent progress in massively multilingual MT is one step closer to reaching this goal, it is becoming evident…
In this work we focus on transferring supervision signals of natural language generation (NLG) tasks between multiple languages. We propose to pretrain the encoder and the decoder of a sequence-to-sequence model under both monolingual and…
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…
We show that unsupervised sequence-segmentation performance can be transferred to extremely low-resource languages by pre-training a Masked Segmental Language Model (Downey et al., 2021) multilingually. Further, we show that this transfer…
Multilingual models have been widely used for cross-lingual transfer to low-resource languages. However, the performance on these languages is hindered by their underrepresentation in the pretraining data. To alleviate this problem, we…
Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool.…
Multilingual semantic parsing is a cost-effective method that allows a single model to understand different languages. However, researchers face a great imbalance of availability of training data, with English being resource rich, and other…
Many language pairs are low resource, meaning the amount and/or quality of available parallel data is not sufficient to train a neural machine translation (NMT) model which can reach an acceptable standard of accuracy. Many works have…
Recently, mT5 - a massively multilingual version of T5 - leveraged a unified text-to-text format to attain state-of-the-art results on a wide variety of multilingual NLP tasks. In this paper, we investigate the impact of incorporating…
Recent speech technologies have led to produce high quality synthesised speech due to recent advances in neural Text to Speech (TTS). However, such TTS models depend on extensive amounts of data that can be costly to produce and is hardly…
While prior work has established that the use of parallel data is conducive for cross-lingual learning, it is unclear if the improvements come from the data itself, or if it is the modeling of parallel interactions that matters. Exploring…
In neural machine translation (NMT), monolingual data in the target language are usually exploited through a method so-called "back-translation" to synthesize additional training parallel data. The synthetic data have been shown helpful to…
Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This presents a challenge for language varieties…
Despite the success of multilingual sequence-to-sequence pretraining, most existing approaches rely on monolingual corpora, and do not make use of the strong cross-lingual signal contained in parallel data. In this paper, we present…