Related papers: Cascaded Text Generation with Markov Transformers
Although neural end-to-end text-to-speech models can synthesize highly natural speech, there is still room for improvements to its efficiency and naturalness. This paper proposes a non-autoregressive neural text-to-speech model augmented…
This paper studies constrained text generation, which is to generate sentences under certain pre-conditions. We focus on CommonGen, the task of generating text based on a set of concepts, as a representative task of constrained text…
Scaling the size of language models to tens of billions of parameters has led to impressive performance on a wide range of tasks. At generation, these models are used auto-regressively, requiring a forward pass for each generated token, and…
The non-autoregressive models have boosted the efficiency of neural machine translation through parallelized decoding at the cost of effectiveness when comparing with the autoregressive counterparts. In this paper, we claim that the…
Text-to-motion generation has attracted increasing attention in the research community recently, with potential applications in animation, virtual reality, robotics, and human-computer interaction. Diffusion and autoregressive models are…
Hybrid tabular-textual question answering (QA) requires reasoning from heterogeneous information, and the types of reasoning are mainly divided into numerical reasoning and span extraction. Current numerical reasoning methods…
Generating sound effects that humans want is an important topic. However, there are few studies in this area for sound generation. In this study, we investigate generating sound conditioned on a text prompt and propose a novel text-to-sound…
Code-switching, the interleaving of two or more languages within a sentence or discourse is pervasive in multilingual societies. Accurate language models for code-switched text are critical for NLP tasks. State-of-the-art data-intensive…
Modern neural sequence generation models are built to either generate tokens step-by-step from scratch or (iteratively) modify a sequence of tokens bounded by a fixed length. In this work, we develop Levenshtein Transformer, a new partially…
Independence assumptions during sequence generation can speed up inference, but parallel generation of highly inter-dependent tokens comes at a cost in quality. Instead of assuming independence between neighbouring tokens…
Speculative decoding has proven to be an efficient solution to large language model (LLM) inference, where the small drafter predicts future tokens at a low cost, and the target model is leveraged to verify them in parallel. However, most…
Due to scarcity of time-series data annotated with descriptive texts, training a model to generate descriptive texts for time-series data is challenging. In this study, we propose a method to systematically generate domain-independent…
Non-Autoregressive Neural Machine Translation (NAT) has achieved significant inference speedup by generating all tokens simultaneously. Despite its high efficiency, NAT usually suffers from two kinds of translation errors: over-translation…
Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential information.…
Recent state-of-the-art Learned Image Compression methods feature spatial context models, achieving great rate-distortion improvements over hyperprior methods. However, the autoregressive context model requires serial decoding, limiting…
The process of translation is ambiguous, in that there are typically many valid trans- lations for a given sentence. This gives rise to significant variation in parallel cor- pora, however, most current models of machine translation do not…
Autoregressive state transitions, where predictions are conditioned on past predictions, are the predominant choice for both deterministic and stochastic sequential models. However, autoregressive feedback exposes the evolution of the…
Standard decoders for neural machine translation autoregressively generate a single target token per time step, which slows inference especially for long outputs. While architectural advances such as the Transformer fully parallelize the…
While large language models have proven effective in a huge range of downstream applications, they often generate text that is problematic or lacks a desired attribute. In this paper, we introduce Reward-Augmented Decoding (RAD), a text…
Although the Transformer translation model (Vaswani et al., 2017) has achieved state-of-the-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer…