Learning to Generate Examples for Semantic Processing Tasks
Even if recent Transformer-based architectures, such as BERT, achieved impressive results in semantic processing tasks, their fine-tuning stage still requires large scale training resources. Usually, Data Augmentation (DA) techniques can help to deal with low resource settings. In Text Classification tasks, the objective of DA is the generation of well-formed sentences that i) represent the desired task category and ii) are novel with respect to existing sentences. In this paper, we propose a neural approach to automatically learn to generate new examples using a pre-trained sequence-to-sequence model. We first learn a task-oriented similarity function that we use to pair similar examples. Then, we use these example pairs to train a model to generate examples. Experiments in low resource settings show that augmenting the training material with the proposed strategy systematically improves the results on text classification and natural language inference tasks by up to 10% accuracy, outperforming existing DA approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationNatural Language Inferencetext-classificationText ClassificationSimilar Papers 제목 키워드 기반
STA: Self-controlled Text Augmentation for Improving Text Classifications
Despite recent advancements in Machine Learning, many tasks still involve working in low-data regimes which can make solving natural language problems difficult. Recently, a number of text augmentation techniques have em…
BenchmarkingText AugmentationA Context Aware Approach for Generating Natural Language Attacks
We study an important task of attacking natural language processing models in a black box setting. We propose an attack strategy that crafts semantically similar adversarial examples on text classification and entailment…
Language ModellingSentencetext-classificationText ClassificationEvaluating the Validity of Word-level Adversarial Attacks with Large Language Models
Deep neural networks exhibit vulnerability to word-level adversarial attacks in natural language processing. Most of these attack methods adopt synonymous substitutions to perturb original samples for crafting adversaria…
Adversarial AttackLanguage ModelingLanguage ModellingLarge Language Model+1Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation
Deep Neural Networks (DNNs) have been widely applied in various recognition tasks. However, recently DNNs have been shown to be vulnerable against adversarial examples, which can mislead DNNs to make arbitrary incorrect …
General ClassificationSegmentationSemantic SegmentationSemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
Deep neural networks (DNNs) have achieved great success in various applications due to their strong expressive power. However, recent studies have shown that DNNs are vulnerable to adversarial examples which are manipula…
AttributeFace RecognitionFace Verification