ColdGANs: Taming Language GANs with Cautious Sampling Strategies

• URL: http://arxiv.org/abs/2006.04643v1
• Date: Mon, 8 Jun 2020 14:48:14 GMT
• Title: ColdGANs: Taming Language GANs with Cautious Sampling Strategies
• Authors: Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano
• Abstract summary: Generative Adversarial Networks (GANs) can mitigate limitations but the discrete nature of text has hindered their application to language generation. We show how classical sampling results in unstable training. We propose to consider alternative exploration strategies in a GAN framework that we name ColdGANs, where we force the sampling to be close to the distribution modes to get smoother learning dynamics. For the first time, to the best of our knowledge, the proposed language GANs compare favorably to MLE, and obtain improvements over the state-of-the-art on three generative tasks.
• Score: 29.943949944682196
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training regimes based on Maximum Likelihood Estimation (MLE) suffer from known limitations, often leading to poorly generated text sequences. At the root of these limitations is the mismatch between training and inference, i.e. the so-called exposure bias, exacerbated by considering only the reference texts as correct, while in practice several alternative formulations could be as good. Generative Adversarial Networks (GANs) can mitigate those limitations but the discrete nature of text has hindered their application to language generation: the approaches proposed so far, based on Reinforcement Learning, have been shown to underperform MLE. Departing from previous works, we analyze the exploration step in GANs applied to text generation, and show how classical sampling results in unstable training. We propose to consider alternative exploration strategies in a GAN framework that we name ColdGANs, where we force the sampling to be close to the distribution modes to get smoother learning dynamics. For the first time, to the best of our knowledge, the proposed language GANs compare favorably to MLE, and obtain improvements over the state-of-the-art on three generative tasks, namely unconditional text generation, question generation, and abstractive summarization.

Related papers

• Enhancing adversarial robustness in Natural Language Inference using explanations [41.46494686136601]
  We cast the spotlight on the underexplored task of Natural Language Inference (NLI) We validate the usage of natural language explanation as a model-agnostic defence strategy through extensive experimentation. We research the correlation of widely used language generation metrics with human perception, in order for them to serve as a proxy towards robust NLI models.
  arXiv  Detail & Related papers  (2024-09-11T17:09:49Z)
• Principled Gradient-based Markov Chain Monte Carlo for Text Generation [77.46654898866291]
  We propose several faithful gradient-based sampling algorithms to sample from the target energy-based text distribution correctly. We demonstrate that faithful samplers are able to generate more fluent text while adhering to the control objectives better.
  arXiv  Detail & Related papers  (2023-12-29T18:00:56Z)
• Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation [21.54093527562344]
  We propose a new strategy where the prior knowledge from large pre-trained models (LPMs) is distilled and leveraged as supervision. Specifically, we introduce Retrieval-augmented Pseudo Sentence Generation (RaPSG), which can efficiently retrieve highly relevant short region descriptions. Experimental results indicate that our method outperforms SOTA captioning models across various settings.
  arXiv  Detail & Related papers  (2023-07-27T10:16:13Z)
• InitialGAN: A Language GAN with Completely Random Initialization [7.642043456676739]
  Generative Adversarial Networks (GANs) are shown to have potential to tackle the notorious exposure bias problem. Existing language GANs adopt estimators like REINFORCE or continuous relaxations to model word probabilities. In this work, we present two techniques to tackle these problems: dropout sampling and fully normalized LSTM.
  arXiv  Detail & Related papers  (2022-08-04T08:56:04Z)
• Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization [94.4409074435894]
  We propose a novel and effective fine-tuning framework, named Layerwise Noise Stability Regularization (LNSR) Specifically, we propose to inject the standard Gaussian noise and regularize hidden representations of the fine-tuned model. We demonstrate the advantages of the proposed method over other state-of-the-art algorithms including L2-SP, Mixout and SMART.
  arXiv  Detail & Related papers  (2022-06-12T04:42:49Z)
• Text Generation with Efficient (Soft) Q-Learning [91.47743595382758]
  Reinforcement learning (RL) offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. We introduce a new RL formulation for text generation from the soft Q-learning perspective. We apply the approach to a wide range of tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
  arXiv  Detail & Related papers  (2021-06-14T18:48:40Z)
• Improving Text Generation with Student-Forcing Optimal Transport [122.11881937642401]
  We propose using optimal transport (OT) to match the sequences generated in training and testing modes. An extension is also proposed to improve the OT learning, based on the structural and contextual information of the text sequences. The effectiveness of the proposed method is validated on machine translation, text summarization, and text generation tasks.
  arXiv  Detail & Related papers  (2020-10-12T19:42:25Z)
• A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation [53.8171136907856]
  We introduce a set of simple yet effective data augmentation strategies dubbed cutoff. cutoff relies on sampling consistency and thus adds little computational overhead. cutoff consistently outperforms adversarial training and achieves state-of-the-art results on the IWSLT2014 German-English dataset.
  arXiv  Detail & Related papers  (2020-09-29T07:08:35Z)
• Unsupervised Text Generation by Learning from Search [86.51619839836331]
  TGLS is a novel framework to unsupervised Text Generation by Learning. We demonstrate the effectiveness of TGLS on two real-world natural language generation tasks, paraphrase generation and text formalization.
  arXiv  Detail & Related papers  (2020-07-09T04:34:48Z)

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.