Unlocking the Power of GANs in Non-Autoregressive Text Generation

• URL: http://arxiv.org/abs/2305.03977v3
• Date: Wed, 02 Oct 2024 06:35:36 GMT
• Title: Unlocking the Power of GANs in Non-Autoregressive Text Generation
• Authors: Da Ren, Yi Cai, Qing Li,
• Abstract summary: We conduct pioneering study of building language GANs based on NAR structures. We propose a GAN-based NAR model, Adversarial Non-autoregressive Transformer (ANT) The experimental results demonstrate that ANT can achieve comparable performance with mainstream models in a single forward pass.
• Score: 12.168952901520461
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative Adversarial Networks (GANs) have been studied in text generation to tackle the exposure bias problem. Despite their remarkable development, they adopt autoregressive structures so suffering from high latency in both training and inference stages. Although GANs have potential to support efficient generation by adopting non-autoregressive (NAR) structures, their explorations in NAR models are extremely limited. In this work, we conduct pioneering study of building language GANs based on NAR structures. We identify two issues that constrain the performance of GAN-based NAR models. Firstly, existing methods of incorporating latent variables provide highly similar representations which cannot describe the diversity of different words in sentences. We tackle this problem by proposing Position-Aware Self-Modulation, providing more diverse and effective representations. Secondly, the attention mechanism in Transformer cannot accurately build word dependencies in the unstable training of GANs, and we adopt Dependency Feed Forward Network to enhance the model capacity in dependency modeling. Armed with these two facilities, we propose a GAN-based NAR model, Adversarial Non-autoregressive Transformer (ANT). The experimental results demonstrate that ANT can achieve comparable performance with mainstream models in a single forward pass and has great potential in various applications like latent interpolation and semi-supervised learning.

Related papers

• Parallelly Tempered Generative Adversarial Networks [7.94957965474334]
  A generative adversarial network (GAN) has been a representative backbone model in generative artificial intelligence (AI) This work analyzes the training instability and inefficiency in the presence of mode collapse by linking it to multimodality in the target distribution. With our newly developed GAN objective function, the generator can learn all the tempered distributions simultaneously.
  arXiv  Detail & Related papers  (2024-11-18T18:01:13Z)
• U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation [48.40120035775506]
  Kolmogorov-Arnold Networks (KANs) reshape the neural network learning via the stack of non-linear learnable activation functions. We investigate, modify and re-design the established U-Net pipeline by integrating the dedicated KAN layers on the tokenized intermediate representation, termed U-KAN. We further delved into the potential of U-KAN as an alternative U-Net noise predictor in diffusion models, demonstrating its applicability in generating task-oriented model architectures.
  arXiv  Detail & Related papers  (2024-06-05T04:13:03Z)
• Common Knowledge Learning for Generating Transferable Adversarial Examples [60.1287733223249]
  This paper focuses on an important type of black-box attacks, where the adversary generates adversarial examples by a substitute (source) model. Existing methods tend to give unsatisfactory adversarial transferability when the source and target models are from different types of DNN architectures. We propose a common knowledge learning (CKL) framework to learn better network weights to generate adversarial examples.
  arXiv  Detail & Related papers  (2023-07-01T09:07:12Z)
• Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting [95.82600221180415]
  Human forecasting in crowds presents the challenges of modelling social interactions and outputting collision-free multimodal distribution. We introduce SGANv2, an improved safety-compliant SGAN architecture equipped with motion-temporal interaction modelling and a transformer-based discriminator design.
  arXiv  Detail & Related papers  (2022-09-25T15:18:56Z)
• A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond [145.43029264191543]
  Non-autoregressive (NAR) generation is first proposed in machine translation (NMT) to speed up inference. While NAR generation can significantly accelerate machine translation, the inference of autoregressive (AR) generation sacrificed translation accuracy. Many new models and algorithms have been designed/proposed to bridge the accuracy gap between NAR generation and AR generation.
  arXiv  Detail & Related papers  (2022-04-20T07:25:22Z)
• Diformer: Directional Transformer for Neural Machine Translation [13.867255817435705]
  Autoregressive (AR) and Non-autoregressive (NAR) models have their own superiority on the performance and latency. We propose the Directional Transformer (Diformer) by jointly modelling AR and NAR into three generation directions. Experiments on 4 WMT benchmarks demonstrate that Diformer outperforms current united-modelling works with more than 1.5 BLEU points for both AR and NAR decoding.
  arXiv  Detail & Related papers  (2021-12-22T02:35:29Z)
• TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition [69.68154370877615]
  The non-autoregressive (NAR) models can get rid of the temporal dependency between the output tokens and predict the entire output tokens in at least one step. To address these two problems, we propose a new model named the two-step non-autoregressive transformer(TSNAT) The results show that the TSNAT can achieve a competitive performance with the AR model and outperform many complicated NAR models.
  arXiv  Detail & Related papers  (2021-04-04T02:34:55Z)
• Transformer-based Conditional Variational Autoencoder for Controllable Story Generation [39.577220559911055]
  We investigate large-scale latent variable models (LVMs) for neural story generation with objectives in two threads: generation effectiveness and controllability. We advocate to revive latent variable modeling, essentially the power of representation learning, in the era of Transformers. Specifically, we integrate latent representation vectors with a Transformer-based pre-trained architecture to build conditional variational autoencoder (CVAE)
  arXiv  Detail & Related papers  (2021-01-04T08:31:11Z)
• Unsupervised Controllable Generation with Self-Training [90.04287577605723]
  controllable generation with GANs remains a challenging research problem. We propose an unsupervised framework to learn a distribution of latent codes that control the generator through self-training. Our framework exhibits better disentanglement compared to other variants such as the variational autoencoder.
  arXiv  Detail & Related papers  (2020-07-17T21:50:35Z)
• DeshuffleGAN: A Self-Supervised GAN to Improve Structure Learning [0.0]
  We argue that one of the crucial points to improve the GAN performance is to be able to provide the model with a capability to learn the spatial structure in data. We introduce a deshuffling task that solves a puzzle of randomly shuffled image tiles, which in turn helps the DeshuffleGAN learn to increase its expressive capacity for spatial structure and realistic appearance.
  arXiv  Detail & Related papers  (2020-06-15T19:06:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.