Related papers: Zero-Shot Joint Modeling of Multiple Spoken-Text-S…

Transfer learning between different language pairs has shown its effectiveness for Neural Machine Translation (NMT) in low-resource scenario. However, existing transfer methods involving a common target language are far from success in the…

Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the…

Massively multilingual models are promising for transfer learning across tasks and languages. However, existing methods are unable to fully leverage training data when it is available in different task-language combinations. To exploit such…

Recently, Text-to-SQL for multi-turn dialogue has attracted great interest. Here, the user input of the current turn is parsed into the corresponding SQL query of the appropriate database, given all previous dialogue history. Current…

Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there's a shortage of parallel documents, although parallel sentences are readily…

Current multimodal machine translation (MMT) systems rely on fully supervised data (i.e models are trained on sentences with their translations and accompanying images). However, this type of data is costly to collect, limiting the…

Zero-shot speaker cloning aims to synthesize speech for any target speaker unseen during TTS system building, given only a single speech reference of the speaker at hand. Although more practical in real applications, the current zero-shot…

Cross-modality data translation has attracted great interest in image computing. Deep generative models (\textit{e.g.}, GANs) show performance improvement in tackling those problems. Nevertheless, as a fundamental challenge in image…

Language style transferring rephrases text with specific stylistic attributes while preserving the original attribute-independent content. One main challenge in learning a style transfer system is a lack of parallel data where the source…

Zero-shot cross-lingual transfer is when a multilingual model is trained to perform a task in one language and then is applied to another language. Although the zero-shot cross-lingual transfer approach has achieved success in various…

We propose a new paradigm for zero-shot learners that is format agnostic, i.e., it is compatible with any format and applicable to a list of language tasks, such as text classification, commonsense reasoning, coreference resolution, and…

We propose a unified model for three inter-related tasks: 1) to \textit{separate} individual sound sources from a mixed music audio, 2) to \textit{transcribe} each sound source to MIDI notes, and 3) to\textit{ synthesize} new pieces based…

The lack of annotated data in many languages is a well-known challenge within the field of multilingual natural language processing (NLP). Therefore, many recent studies focus on zero-shot transfer learning and joint training across…

Speech and text are two major forms of human language. The research community has been focusing on mapping speech to text or vice versa for many years. However, in the field of language modeling, very little effort has been made to model…

Most existing zero-shot learning approaches exploit transfer learning via an intermediate-level semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no annotation. A…

Zero-shot voice conversion (VC) aims to transform source speech into arbitrary unseen target voice while keeping the linguistic content unchanged. Recent VC methods have made significant progress, but semantic losses in the decoupling…

Natural language processing methods have several applications in automated auditing, including document or passage classification, information retrieval, and question answering. However, training such models requires a large amount of…

Current disfluency detection models focus on individual utterances each from a single speaker. However, numerous discontinuity phenomena in spoken conversational transcripts occur across multiple turns, hampering human readability and the…

Finetuning pretrained models on downstream generation tasks often leads to catastrophic forgetting in zero-shot conditions. In this work, we focus on summarization and tackle the problem through the lens of language-independent…

Transformer-based pre-trained language models (PLMs) have achieved remarkable performance in various natural language processing (NLP) tasks. However, pre-training such models can take considerable resources that are almost only available…