Contrastive Learning with Adversarial Perturbations for Conditional Text Generation

• URL: http://arxiv.org/abs/2012.07280v6
• Date: Wed, 10 Mar 2021 13:27:34 GMT
• Title: Contrastive Learning with Adversarial Perturbations for Conditional Text Generation
• Authors: Seanie Lee, Dong Bok Lee, Sung Ju Hwang
• Abstract summary: We propose a principled method to generate positive and negative samples for contrastive learning of seq2seq models. Specifically, we generate negative examples by adding small perturbations to the input sequence to minimize its conditional likelihood. We empirically show that our proposed method significantly improves the generalization of the seq2seq on three text generation tasks.
• Score: 49.055659008469284
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, sequence-to-sequence (seq2seq) models with the Transformer architecture have achieved remarkable performance on various conditional text generation tasks, such as machine translation. However, most of them are trained with teacher forcing with the ground truth label given at each time step, without being exposed to incorrectly generated tokens during training, which hurts its generalization to unseen inputs, that is known as the "exposure bias" problem. In this work, we propose to mitigate the conditional text generation problem by contrasting positive pairs with negative pairs, such that the model is exposed to various valid or incorrect perturbations of the inputs, for improved generalization. However, training the model with naive contrastive learning framework using random non-target sequences as negative examples is suboptimal, since they are easily distinguishable from the correct output, especially so with models pretrained with large text corpora. Also, generating positive examples requires domain-specific augmentation heuristics which may not generalize over diverse domains. To tackle this problem, we propose a principled method to generate positive and negative samples for contrastive learning of seq2seq models. Specifically, we generate negative examples by adding small perturbations to the input sequence to minimize its conditional likelihood, and positive examples by adding large perturbations while enforcing it to have a high conditional likelihood. Such "hard" positive and negative pairs generated using our method guides the model to better distinguish correct outputs from incorrect ones. We empirically show that our proposed method significantly improves the generalization of the seq2seq on three text generation tasks - machine translation, text summarization, and question generation.

Related papers

• Negative-Prompt-driven Alignment for Generative Language Model [34.191590966148816]
  We propose NEgative-prompt-driven AlignmenT to guide language models away from undesirable behaviors. NEAT explicitly penalizes the model for producing harmful outputs, guiding it not only toward desirable behaviors but also steering it away from generating undesirable, biased responses. Extensive experiments validate NEAT's effectiveness in significantly enhancing language models' alignment with human values and preferences.
  arXiv  Detail & Related papers  (2024-10-16T03:30:09Z)
• A Constraint-Enforcing Reward for Adversarial Attacks on Text Classifiers [10.063169009242682]
  We train an encoder-decoder paraphrase model to generate adversarial examples. We adopt a reinforcement learning algorithm and propose a constraint-enforcing reward. We show how key design choices impact the generated examples and discuss the strengths and weaknesses of the proposed approach.
  arXiv  Detail & Related papers  (2024-05-20T09:33:43Z)
• Generating Enhanced Negatives for Training Language-Based Object Detectors [86.1914216335631]
  We propose to leverage the vast knowledge built into modern generative models to automatically build negatives that are more relevant to the original data. Specifically, we use large-language-models to generate negative text descriptions, and text-to-image diffusion models to also generate corresponding negative images. Our experimental analysis confirms the relevance of the generated negative data, and its use in language-based detectors improves performance on two complex benchmarks.
  arXiv  Detail & Related papers  (2023-12-29T23:04:00Z)
• SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples [23.77077091225583]
  Self-labeled Counterfactuals for Extrapolating to Negative Examples (SCENE) is an automatic method for synthesizing training data. With access to only answerable training examples, SCENE can close 69.6% of the performance gap on SQuAD 2.0.
  arXiv  Detail & Related papers  (2023-05-13T19:30:58Z)
• Language Model Pre-training on True Negatives [109.73819321246062]
  Discriminative pre-trained language models (PLMs) learn to predict original texts from intentionally corrupted ones. Existing PLMs simply treat all corrupted texts as equal negative without any examination. We design enhanced pre-training methods to counteract false negative predictions and encourage pre-training language models on true negatives.
  arXiv  Detail & Related papers  (2022-12-01T12:24:19Z)
• Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality [84.94877848357896]
  Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. We analyze this behavior of seq2seq models and identify two contributing factors: a lack of mutual exclusivity bias and the tendency to memorize whole examples. We show substantial empirical improvements using standard sequence-to-sequence models on two widely-used compositionality datasets.
  arXiv  Detail & Related papers  (2022-11-28T17:36:41Z)
• Generating Sequences by Learning to Self-Correct [64.0249217590888]
  Self-Correction decouples an imperfect base generator from a separate corrector that learns to iteratively correct imperfect generations. We show that Self-Correction improves upon the base generator in three diverse generation tasks.
  arXiv  Detail & Related papers  (2022-10-31T18:09:51Z)
• Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives [17.90820242798732]
  Unsupervised contrastive learning methods still lag far behind the supervised counterparts. We propose switch-case augmentation to flip the case of the first letter of randomly selected words in a sentence. For negative samples, we sample hard negatives from the whole dataset based on a pre-trained language model.
  arXiv  Detail & Related papers  (2022-06-06T09:46:12Z)
• Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation [102.99799162482283]
  We present instance-wise hard Negative Example Generation for Contrastive learning in Unpaired image-to-image Translation (NEGCUT) Specifically, we train a generator to produce negative examples online. The generator is novel from two perspectives: 1) it is instance-wise which means that the generated examples are based on the input image, and 2) it can generate hard negative examples since it is trained with an adversarial loss.
  arXiv  Detail & Related papers  (2021-08-10T09:44:59Z)

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.