Related papers: NAST: A Non-Autoregressive Generator with Word Ali…

In this article we show how the problem of neural text generation can be constructively reformulated in terms of transitions between the states of a finite-state machine. This framework leads to an efficient approach to guiding text…

Current speech generation research can be categorized into two primary classes: non-autoregressive and autoregressive. The fundamental distinction between these approaches lies in the duration prediction strategy employed for…

Paraphrase generation has benefited extensively from recent progress in the designing of training objectives and model architectures. However, previous explorations have largely focused on supervised methods, which require a large amount of…

Spoken Language Understanding (SLU), a core component of the task-oriented dialogue system, expects a shorter inference latency due to the impatience of humans. Non-autoregressive SLU models clearly increase the inference speed but suffer…

Disentangling the content and style in the latent space is prevalent in unpaired text style transfer. However, two major issues exist in most of the current neural models. 1) It is difficult to completely strip the style information from…

Current language models demonstrate remarkable proficiency in text generation. However, for many applications it is desirable to control attributes, such as sentiment, or toxicity, of the generated language -- ideally tailored towards each…

Unsupervised Text Style Transfer (UTST) has emerged as a critical task within the domain of Natural Language Processing (NLP), aiming to transfer one stylistic aspect of a sentence into another style without changing its semantics, syntax,…

Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of…

Large pre-trained language models are capable of generating varied and fluent texts. Starting from the prompt, these models generate a narrative that can develop unpredictably. The existing methods of controllable text generation, which…

The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. The problem so far has been framed in a standard supervised way and consists…

Although neural machine translation models reached high translation quality, the autoregressive nature makes inference difficult to parallelize and leads to high translation latency. Inspired by recent refinement-based approaches, we…

Non-parallel text style transfer has attracted increasing research interests in recent years. Despite successes in transferring the style based on the encoder-decoder framework, current approaches still lack the ability to preserve the…

Autoregressive decoding strategy is a commonly used method for text generation tasks with pre-trained language models, while early-exiting is an effective approach to speedup the inference stage. In this work, we propose a novel decoding…

Adapting a large language model for multiple-attribute text style transfer via fine-tuning can be challenging due to the significant amount of computational resources and labeled data required for the specific task. In this paper, we…

In this work, we address the Text-to-Speech (TTS) task by proposing a non-autoregressive architecture called EfficientTTS. Unlike the dominant non-autoregressive TTS models, which are trained with the need of external aligners, EfficientTTS…

Non-autoregressive translation (NAT) models remove the dependence on previous target tokens and generate all target tokens in parallel, resulting in significant inference speedup but at the cost of inferior translation accuracy compared to…

Despite their generative power, diffusion models struggle to maintain style consistency across images conditioned on the same style prompt, hindering their practical deployment in creative workflows. While several training-free methods…

Diffusion models have become the dominant approach for visual generation. They are trained by denoising a Markovian process which gradually adds noise to the input. We argue that the Markovian property limits the model's ability to fully…

We consider the problem of automatically generating textual paraphrases with modified attributes or properties, focusing on the setting without parallel data (Hu et al., 2017; Shen et al., 2017). This setting poses challenges for…

Non-autoregressive neural machine translation (NAT) usually employs sequence-level knowledge distillation using autoregressive neural machine translation (AT) as its teacher model. However, a NAT model often outputs shorter sentences than…