paper-with-me

Papers

Diffusion-NAT: Self-Prompting Discrete Diffusion for Non-Autoregressive Text Generation

2023-05-06 · Kun Zhou, YiFan Li, Wayne Xin Zhao, Ji-Rong Wen

Recently, continuous diffusion models (CDM) have been introduced into non-autoregressive (NAR) text-to-text generation. However, the discrete nature of text increases the difficulty of CDM to generate coherent and fluent texts, and also causes the incompatibility problem between CDM and advanced NLP techniques, especially the popular pre-trained language models~(PLMs). To solve it, we propose Diffusion-NAT, which introduces discrete diffusion models~(DDM) into NAR text-to-text generation and integrates BART to improve the performance. By revising the decoding process of BART and the typical settings of DDM, we unify the inference process of BART and the denoising process of DDM into the same NAR masked tokens recovering task. In this way, DDM can rely on BART to perform denoising, which can benefit from both the rich pre-learned knowledge of BART and the iterative refining paradigm of DDM. Besides, we also propose the iterative self-prompting strategy to further improve the generation quality. Experimental results on 7 datasets show that our approach can outperform competitive NAR methods, and even surpass autoregressive methods. Our code and data will be publicly released.

📄 PDF Abstract BibTeX arXiv:2305.04044

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingText Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Flexible-length Text Infilling for Discrete Diffusion Models

2025-06-16 · Andrew Zhang, Anushka Sivakumar, Chiawei Tang, Chris Thomas

Discrete diffusion models are a new class of text generators that offer advantages such as bidirectional context use, parallelizable generation, and flexible prompting compared to autoregressive models. However, a critic…

PositionText Infilling

Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution

2023-10-25 · Aaron Lou, Chenlin Meng, Stefano Ermon

Despite their groundbreaking performance for many generative modeling tasks, diffusion models have fallen short on discrete data domains such as natural language. Crucially, standard diffusion models rely on the well-est…

DenoisingLanguage ModelingLanguage Modelling

Planned Diffusion

2025-10-20 · Daniel Israel, Tian Jin, Ellie Cheng, Guy Van den Broeck 외 arxiv

Most large language models are autoregressive: they generate tokens one at a time. Discrete diffusion language models can generate multiple tokens in parallel, but sampling from them requires a denoising order: a strateg…

Instruction Following

TESS: Text-to-Text Self-Conditioned Simplex Diffusion

2023-05-15 · Rabeeh Karimi Mahabadi, Hamish Ivison, Jaesung Tae, James Henderson 외

Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various continuous domains. However, applying continuous diffusion models to natural language remains challenging due t…

Natural Language UnderstandingParaphrase GenerationQuestion GenerationQuestion-Generation+2

Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning

2022-08-08 · Ting Chen, Ruixiang Zhang, Geoffrey Hinton

We present Bit Diffusion: a simple and generic approach for generating discrete data with continuous state and continuous time diffusion models. The main idea behind our approach is to first represent the discrete data a…

Image CaptioningImage Generation