一种可解释的方法,用于口语成绩单和书面文本的自动分类.
Mattias Wahde1, Marco L Della Vedova1, Marco Virgolin2
1Chalmers University of Technology, 412 96 Gothenburg, Sweden.
Evolutionary intelligence
|June 26, 2023
概括
这项研究比较了口语和书面语言的文本分类. 一个新的可解释线性分类器实现了接近深度学习模型的性能,在可解释性是关键时提供了可靠的替代方案.
科学领域:
- 自然语言处理自然语言处理.
- 计算语言学 计算语言学
- 机器学习 机器学习
背景情况:
- 区分口语和书面语言对于文本分类至关重要.
- 像DistilBERT这样的深度神经网络 (DNN) 是常见的,但往往缺乏可解释性.
- 经典的机器学习方法可能会提供更多的透明度.
研究的目的:
- 为了比较口语与书面语言的文本分类性能.
- 介绍和评估一个新的,可解释的线性分类器.
- 评估经典和基于DNN的方法之间的性能差距.
主要方法:
- 用了广播节目转录 (口语) 和维基百科文章 (书面) 来创建一个新的数据集.
- 开发了一种具有广泛n-gram特征的线性分类器.
- 将新型分类器的准确性和信心度量与DistilBERT进行了比较.
- 对口语和书面文本的填空任务进行了DistilBERT的评估.
主要成果:
- 可解释的线性分类器实现了0.02 DistilBERT. 的精度.
- 拟议的分类器包括用于可靠性评估的综合信任度.
- 对于这两种语言类型,DistilBERT在填空任务上表现相似.
- 经典和DNN方法之间的性能差距可以显著缩小.
结论:
- 经典的文本分类方法,随着改进,可以与DNN性能竞争.
- 解释性是选择高风险决策分类方法的关键因素.
- 方法之间的选择取决于透明度和可解释性的必要性.
相关概念视频
01:30Classification of Signals
556
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
556
01:26Classification of Systems-I
221
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
221
01:28Methods of Classification and Identification
55
Bacterial identification relies on a diverse array of techniques to classify and understand microorganisms, each tailored to uncover specific characteristics. Traditional morphological approaches, while still valuable, are limited for closely related or structurally simple organisms. Modern methods integrate biochemical, serological, genetic, and advanced molecular tools to achieve greater accuracy.Morphological and Biochemical TechniquesMorphological characteristics, such as cell shape and...
55
02:07Improving Translational Accuracy
2.6K
2.6K
01:31Classification of Systems-II
183
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
183
02:23Master Transcription Regulators
2.3K
2.3K