Related papers: PEACH: Pre-Training Sequence-to-Sequence Multiling…
Agents that can follow language instructions are expected to be useful in a variety of situations such as navigation. However, training neural network-based agents requires numerous paired trajectories and languages. This paper proposes…
Large pre-trained models have revolutionized natural language processing (NLP) research and applications, but high training costs and limited data resources have prevented their benefits from being shared equally amongst speakers of all the…
We exploit the pre-trained seq2seq model mBART for multilingual text style transfer. Using machine translated data as well as gold aligned English sentences yields state-of-the-art results in the three target languages we consider. Besides,…
Nowadays, training end-to-end neural models for spoken language translation (SLT) still has to confront with extreme data scarcity conditions. The existing SLT parallel corpora are indeed orders of magnitude smaller than those available for…
We introduce MARGE, a pre-trained sequence-to-sequence model learned with an unsupervised multi-lingual multi-document paraphrasing objective. MARGE provides an alternative to the dominant masked language modeling paradigm, where we…
Recent studies have demonstrated that pre-trained cross-lingual models achieve impressive performance in downstream cross-lingual tasks. This improvement benefits from learning a large amount of monolingual and parallel corpora. Although it…
Despite considerable progress, the advancement of Panoptic Narrative Grounding (PNG) remains hindered by costly annotations. In this paper, we introduce a novel Semi-Supervised Panoptic Narrative Grounding (SS-PNG) learning scheme,…
For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such…
Recent advances in neural TTS have led to models that can produce high-quality synthetic speech. However, these models typically require large amounts of training data, which can make it costly to produce a new voice with the desired…
Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain success in the situation where a lot of high-quality speech plus their corresponding transcriptions are available. However, laborious paired data collection processes…
Mechanisms for continued self-improvement of language models without external supervision remain an open challenge. We propose Peer-Predictive Self-Training (PST), a label-free fine-tuning framework in which multiple language models improve…
Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora. However,…
Transfer learning from a high-resource language pair `parent' has been proven to be an effective way to improve neural machine translation quality for low-resource language pairs `children.' However, previous approaches build a custom…
Large language models (LLMs) have demonstrated impressive translation capabilities even without being explicitly trained on parallel data. This remarkable property has led some to believe that parallel data is no longer necessary for…
Can pre-trained BERT for one language and GPT for another be glued together to translate texts? Self-supervised training using only monolingual data has led to the success of pre-trained (masked) language models in many NLP tasks. However,…
Subword modeling for zero-resource languages aims to learn low-level representations of speech audio without using transcriptions or other resources from the target language (such as text corpora or pronunciation dictionaries). A good…
In the development of neural text-to-speech systems, model pre-training with a large amount of non-target speakers' data is a common approach. However, in terms of ultimately achieved system performance for target speaker(s), the actual…
Learning what to share between tasks has been a topic of great importance recently, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important for multilingual applications, as…
Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…
We propose a method of curating high-quality comparable training data for low-resource languages with monolingual annotators. Our method involves using a carefully selected set of images as a pivot between the source and target languages by…