VIP内容
简介：
基于语言模型的预训练模型，如BERT，在不同的NLP任务中提供了显著的收益。在本文中，我们研究了不同类型的基于自回归模型(GPT-2)、自编码器模型(BERT)和seq2seq模型(BART)等用于条件数据增强的预训练变压器模型。我们表明，将类标签前置到文本序列提供了一种简单而有效的方法来设置预训练模型的条件，以便进行数据扩充。在三个分类基准上，预先训练的Seq2Seq模型优于其他模型。此外，我们还探讨了不同的基于预训练模型的数据扩充在数据多样性方面是如何不同的，以及这些方法如何很好地保存类标签信息。
Data Augmentation using Pre-trained Transformer Models
热门内容
最新内容
When making an online purchase, it becomes important for the customer to read the product reviews carefully and make a decision based on that. However, reviews can be lengthy, may contain repeated, or sometimes irrelevant information that does not help in decision making. In this paper, we introduce MRCBert, a novel unsupervised method to generate summaries from product reviews. We leverage Machine Reading Comprehension, i.e. MRC, approach to extract relevant opinions and generate both rating-wise and aspect-wise summaries from reviews. Through MRCBert we show that we can obtain reasonable performance using existing models and transfer learning, which can be useful for learning under limited or low resource scenarios. We demonstrated our results on reviews of a product from the Electronics category in the Amazon Reviews dataset. Our approach is unsupervised as it does not require any domain-specific dataset, such as the product review dataset, for training or fine-tuning. Instead, we have used SQuAD v1.1 dataset only to fine-tune BERT for the MRC task. Since MRCBert does not require a task-specific dataset, it can be easily adapted and used in other domains.
最新论文
When making an online purchase, it becomes important for the customer to read the product reviews carefully and make a decision based on that. However, reviews can be lengthy, may contain repeated, or sometimes irrelevant information that does not help in decision making. In this paper, we introduce MRCBert, a novel unsupervised method to generate summaries from product reviews. We leverage Machine Reading Comprehension, i.e. MRC, approach to extract relevant opinions and generate both rating-wise and aspect-wise summaries from reviews. Through MRCBert we show that we can obtain reasonable performance using existing models and transfer learning, which can be useful for learning under limited or low resource scenarios. We demonstrated our results on reviews of a product from the Electronics category in the Amazon Reviews dataset. Our approach is unsupervised as it does not require any domain-specific dataset, such as the product review dataset, for training or fine-tuning. Instead, we have used SQuAD v1.1 dataset only to fine-tune BERT for the MRC task. Since MRCBert does not require a task-specific dataset, it can be easily adapted and used in other domains.