Adding A Filter Based on The Discriminator to Improve Unconditional Text Generation

• URL: http://arxiv.org/abs/2004.02135v5
• Date: Mon, 22 Jun 2020 04:59:43 GMT
• Title: Adding A Filter Based on The Discriminator to Improve Unconditional Text Generation
• Authors: Xingyuan Chen, Ping Cai, Peng Jin, Hongjun Wang, Xinyu Dai, Jiajun Chen
• Abstract summary: The autoregressive language model (ALM) trained with maximum likelihood estimation (MLE) is widely used in unconditional text generation. Due to exposure bias, the generated texts still suffer from low quality and diversity. Some research shows a discriminator can detect this discrepancy. We propose a novel mechanism by adding a filter which has the same input as the discriminator.
• Score: 35.122864215334836
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The autoregressive language model (ALM) trained with maximum likelihood estimation (MLE) is widely used in unconditional text generation. Due to exposure bias, the generated texts still suffer from low quality and diversity. This presents statistically as a discrepancy between the real text and generated text. Some research shows a discriminator can detect this discrepancy. Because the discriminator can encode more information than the generator, discriminator has the potentiality to improve generator. To alleviate the exposure bias, generative adversarial networks (GAN) use the discriminator to update the generator's parameters directly, but they fail by being evaluated precisely. A critical reason for the failure is the difference between the discriminator input and the ALM input. We propose a novel mechanism by adding a filter which has the same input as the discriminator. First, discriminator detects the discrepancy signals and passes to filter directly (or by learning). Then, we use the filter to reject some generated samples with a sampling-based method. Thus, the original generative distribution is revised to reduce the discrepancy. Two ALMs, RNN-based and Transformer-based, are experimented. Evaluated precisely by three metrics, our mechanism consistently outperforms the ALMs and all kinds of GANs across two benchmark data sets.

Related papers

• Prompt Optimization via Adversarial In-Context Learning [51.18075178593142]
  adv-ICL is implemented as a two-player game between a generator and a discriminator. The generator tries to generate realistic enough output to fool the discriminator. We show that adv-ICL results in significant improvements over state-of-the-art prompt optimization techniques.
  arXiv  Detail & Related papers  (2023-12-05T09:44:45Z)
• Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation [55.27563366506407]
  We introduce a discriminator-free adversarial learning network (DALN) for unsupervised domain adaptation (UDA) DALN achieves explicit domain alignment and category distinguishment through a unified objective. DALN compares favorably against the existing state-of-the-art (SOTA) methods on a variety of public datasets.
  arXiv  Detail & Related papers  (2022-04-08T04:40:18Z)
• Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts [10.647970046084916]
  We argue that training stable discriminators produces expressive loss functions that we can re-use at inference to detect and correct segmentation mistakes. We show that we can combine discriminators with image reconstruction costs (via decoders) to further improve the model. Our method is simple and improves the test-time performance of pre-trained GANs.
  arXiv  Detail & Related papers  (2021-08-26T17:31:46Z)
• Revealing the Distributional Vulnerability of Discriminators by Implicit Generators [36.66825830101456]
  In deep neural learning, a discriminator trained on in-distribution (ID) samples may make high-confidence predictions on out-of-distribution (OOD) samples. We propose a general approach for itfine-tuning discriminators by implicit generators (FIG) It improves the ability of a standard discriminator in distinguishing ID and OOD samples by generating and penalizing its specific OOD samples.
  arXiv  Detail & Related papers  (2021-08-23T07:18:50Z)
• Sampling-Decomposable Generative Adversarial Recommender [84.05894139540048]
  We propose a Sampling-Decomposable Generative Adversarial Recommender (SD-GAR) In the framework, the divergence between some generator and the optimum is compensated by self-normalized importance sampling. We extensively evaluate the proposed algorithm with five real-world recommendation datasets.
  arXiv  Detail & Related papers  (2020-11-02T13:19:10Z)
• Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator [85.68825725223873]
  Generative Adversarial Networks (GANs) have shown great promise in modeling high dimensional data. We introduce the Discriminator Contrastive Divergence, which is well motivated by the property of WGAN's discriminator. We demonstrate the benefits of significant improved generation on both synthetic data and several real-world image generation benchmarks.
  arXiv  Detail & Related papers  (2020-04-05T01:50:16Z)
• Self-Adversarial Learning with Comparative Discrimination for Text Generation [111.18614166615968]
  We propose a novel self-adversarial learning (SAL) paradigm for improving GANs' performance in text generation. During training, SAL rewards the generator when its currently generated sentence is found to be better than its previously generated samples. Experiments on text generation benchmark datasets show that our proposed approach substantially improves both the quality and the diversity.
  arXiv  Detail & Related papers  (2020-01-31T07:50:25Z)
• Reject Illegal Inputs with Generative Classifier Derived from Any Discriminative Classifier [7.33811357166334]
  Supervised Deep Infomax(M) is a scalable end-to-end framework to learn generative classifiers. We propose a modification of SDIM termed SDIM-emphlogit.
  arXiv  Detail & Related papers  (2020-01-02T15:11:58Z)

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.