Rank over Class: The Untapped Potential of Ranking in Natural Language Processing
Rank over Class: The Untapped Potential of Ranking in Natural Language Processing
复制标题
DOI：
10.1109/bigdata52589.2021.9671386
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Amir Atapour-Abarghouei;Stephen Bonner;A. Mcgough
中科院分区：
文献类型：
--
作者：
Amir Atapour-Abarghouei;Stephen Bonner;A. Mcgough
长期以来，文本分类一直是自然语言处理(NLP)中的主要内容，其应用程序跨越了不同的领域，如情感分析、推荐系统和垃圾邮件检测。有了这样一个强大的解决方案，人们往往会忍不住把它作为解决所有NLP问题的首选工具，因为当你拿着锤子时，一切看起来都像钉子。然而，我们在这里认为，目前使用分类解决的许多任务实际上被硬塞进了分类模型中，如果我们将它们作为一个排名问题来处理，我们不仅可以改进模型，而且我们可以获得更好的性能。我们提出了一种新的端到端排序方法，该方法由一个转换器网络组成，该网络负责产生一对文本序列的表示，这些文本序列又被传递到上下文聚合网络，该网络输出排序分数，用于根据一些相关性概念来确定序列的排序。我们在公开可用的数据集上进行了大量的实验，并研究了排序在经常使用分类解决的问题中的应用。在一个严重倾斜的情感分析数据集上的实验中，将排序结果转换为分类标签比最新的文本分类产生了大约22%的改进，展示了在某些场景下文本排序相对于文本分类的有效性。
Text classification has long been a staple within Natural Language Processing (NLP) with applications spanning across diverse areas such as sentiment analysis, recommender systems and spam detection. With such a powerful solution, it is often tempting to use it as the go-to tool for all NLP problems since when you are holding a hammer, everything looks like a nail. However, we argue here that many tasks which are currently addressed using classification are in fact being shoehorned into a classification mould and that if we instead address them as a ranking problem, we not only improve the model, but we achieve better performance. We propose a novel end-to-end ranking approach consisting of a Transformer network responsible for producing representations for a pair of text sequences, which are in turn passed into a context aggregating network outputting ranking scores used to determine an ordering to the sequences based on some notion of relevance. We perform numerous experiments on publicly-available datasets and investigate the applications of ranking in problems often solved using classification. In an experiment on a heavily- skewed sentiment analysis dataset, converting ranking results to classification labels yields an approximately 22% improvement over state-of-the-art text classification, demonstrating the efficacy of text ranking over text classification in certain scenarios.