Related papers: Text Style Transfer Back-Translation
Text style transfer aims to paraphrase a sentence in one style into another style while preserving content. Due to lack of parallel training data, state-of-art methods are unsupervised and rely on large datasets that share content.…
Back-translation is widely known for its effectiveness in neural machine translation when there is little to no parallel data. In this approach, a source-to-target model is coupled with a target-to-source model trained in parallel. The…
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…
Sign language gloss translation aims to translate the sign glosses into spoken language texts, which is challenging due to the scarcity of labeled gloss-text parallel data. Back translation (BT), which generates pseudo-parallel data by…
How to solve the data scarcity problem for end-to-end speech-to-text translation (ST)? It's well known that data augmentation is an efficient method to improve performance for many tasks by enlarging the dataset. In this paper, we propose…
Preservation of domain knowledge from the source to target is crucial in any translation workflow. It is common in the translation industry to receive highly specialized projects, where there is hardly any parallel in-domain data. In such…
It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, often requiring large amounts of auxiliary data to achieve competitive results. An effective method of generating auxiliary…
How to achieve better end-to-end speech translation (ST) by leveraging (text) machine translation (MT) data? Among various existing techniques, multi-task learning is one of the effective ways to share knowledge between ST and MT in which…
Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…
Translating text into a language unknown to the text's author, dubbed outbound translation, is a modern need for which the user experience has significant room for improvement, beyond the basic machine translation facility. We demonstrate…
Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive…
Multilingual Machine Translation (MMT) benefits from knowledge transfer across different language pairs. However, improvements in one-to-many translation compared to many-to-one translation are only marginal and sometimes even negligible.…
End-to-end neural TTS training has shown improved performance in speech style transfer. However, the improvement is still limited by the training data in both target styles and speakers. Inadequate style transfer performance occurs when the…
Building conversational speech recognition systems for new languages is constrained by the availability of utterances that capture user-device interactions. Data collection is both expensive and limited by the speed of manual transcription.…
Back-translation is a critical component of Unsupervised Neural Machine Translation (UNMT), which generates pseudo parallel data from target monolingual data. A UNMT model is trained on the pseudo parallel data with translated source, and…
Text style transfer is the task of transferring the style of text having certain stylistic attributes, while preserving non-stylistic or content information. In this work we introduce the Generative Style Transformer (GST) - a new approach…
Machine-translated text plays a crucial role in the communication of people using different languages. However, adversaries can use such text for malicious purposes such as plagiarism and fake review. The existing methods detected a…
Machine Translation (MT) tools are widely used today, often in contexts where professional translators are not present. Despite progress in MT technology, a gap persists between system development and real-world usage, particularly for…
This paper focuses on text detoxification, i.e., automatically converting toxic text into non-toxic text. This task contributes to safer and more respectful online communication and can be considered a Text Style Transfer (TST) task, where…
Edit-based approaches have recently shown promising results on multiple monolingual sequence transduction tasks. In contrast to conventional sequence-to-sequence (Seq2Seq) models, which learn to generate text from scratch as they are…