论文标题
语言表示模型用于细粒情感分类
Language Representation Models for Fine-Grained Sentiment Classification
论文作者
论文摘要
情感分类是在几乎任何领域的应用程序中快速发展的研究领域。尽管各种模型和数据集在二进制分类的任务中表现出很高的准确性，但细粒情感分类的任务仍然是具有重大改进空间的领域。分析SST-5数据集，Munikar等人的先前工作。 （2019年）表明，嵌入工具BERT允许一个简单的模型实现最新的精度。自从该论文以来，已经发表了几种BERT替代方案，其中三个主要是Albert（Lan等，2019），Distilbert（Sanh等，2019）和Roberta（Liuetal。2019）。尽管这些模型在流行的基准胶，小队和种族上报告了对BERT的一些改进，但它们尚未应用于细粒度的分类任务。在本文中，我们通过复制Munikar等人的BERT模型并将嵌入层交换为替代模型，从而检查了应用于新任务时的改进是否成立。在实验中，我们发现，阿尔伯特（Albert）的准确性损失明显比其他任务所报告的要高得多，Distilbert的准确性损失类似于其对其他任务的损失，同时是训练最快的模型，而Roberta则在SST-5根水平（60.2％）上达到了预测的最新预测准确性。
Sentiment classification is a quickly advancing field of study with applications in almost any field. While various models and datasets have shown high accuracy inthe task of binary classification, the task of fine-grained sentiment classification is still an area with room for significant improvement. Analyzing the SST-5 dataset,previous work by Munikar et al. (2019) showed that the embedding tool BERT allowed a simple model to achieve state-of-the-art accuracy. Since that paper, several BERT alternatives have been published, with three primary ones being AlBERT (Lan et al., 2019), DistilBERT (Sanh et al. 2019), and RoBERTa (Liu etal. 2019). While these models report some improvement over BERT on the popular benchmarks GLUE, SQuAD, and RACE, they have not been applied to the fine-grained classification task. In this paper, we examine whether the improvements hold true when applied to a novel task, by replicating the BERT model from Munikar et al., and swapping the embedding layer to the alternative models. Over the experiments, we found that AlBERT suffers significantly more accuracy loss than reported on other tasks, DistilBERT has accuracy loss similar to their reported loss on other tasks while being the fastest model to train, and RoBERTa reaches anew state-of-the-art accuracy for prediction on the SST-5 root level (60.2%).
