Book contents
- Frontmatter
- Contents
- List of Figures
- List of Tables
- List of Background Boxes
- Preface
- List of Abbreviations
- 1Introduction
- 2Julia Fundamentals
- 3The Dataset
- 4Representing Words’ Forms
- 5Representing Words’ Meanings
- 6Computing Comprehension and Production Mappings
- 7Evaluating Mapping Accuracy
- 8Producing Forms
- 9Outputting Modelling Results
- 10Cross-Validation
- 11Deep Discriminative Learning in JudiLing
- 12Worked Examples – Internal Validation
- 13Predicting Behavioural Data with the DLM
- 14Worked Examples: External Validation
- 15No Escape from Morphemes?
- 16Further Topics
- 17Concluding Remarks
- References
- Index
11 - Deep Discriminative Learning in JudiLing
Published online by Cambridge University Press: 15 May 2026
Book contents
- Frontmatter
- Contents
- List of Figures
- List of Tables
- List of Background Boxes
- Preface
- List of Abbreviations
- 1Introduction
- 2Julia Fundamentals
- 3The Dataset
- 4Representing Words’ Forms
- 5Representing Words’ Meanings
- 6Computing Comprehension and Production Mappings
- 7Evaluating Mapping Accuracy
- 8Producing Forms
- 9Outputting Modelling Results
- 10Cross-Validation
- 11Deep Discriminative Learning in JudiLing
- 12Worked Examples – Internal Validation
- 13Predicting Behavioural Data with the DLM
- 14Worked Examples: External Validation
- 15No Escape from Morphemes?
- 16Further Topics
- 17Concluding Remarks
- References
- Index
Summary
JudiLing also offers the option of replacing the linear mappings with mappings implemented with multiple non-linear layers, often referred to as deep learning models. In this chapter, we provide a brief introduction to how DDL is implemented in JudiLing. However, this chapter is not intended as an introduction to machine learning. Therefore, even though we will introduce machine learning concepts briefly (and Box 11.1 contains a glossary of important terms, which are highlighted in italics on first mention in this chapter), we refer the interested reader to work such as Trask (2019) and Goodfellow et al. (2016) to learn more about the various components of deep learning models and their training regimes.
Information
- Type
- Chapter
- Information
- The Discriminative LexiconTheory, Implementation in the Julia Package JudiLing, and Applications, pp. 106 - 126Publisher: Cambridge University PressPrint publication year: 2026
Accessibility standard: WCAG 2.1 A
Why this information is here
This section outlines the accessibility features of this content - including support for screen readers, full keyboard navigation and high-contrast display options. This may not be relevant for you.Accessibility Information
The PDF of this chapter complies with version 2.1 of the
Web Content Accessibility Guidelines
(WCAG), covering newer accessibility requirements and improved
user experiences and meets the basic
(A)
level of WCAG compliance, addressing essential accessibility barriers.
Content Navigation
Table of contents navigation
Allows you to navigate directly to chapters, sections, or non‐text items through a linked table of contents, reducing the need for extensive scrolling.
Allows you to navigate directly to chapters, sections, or non‐text items through a linked table of contents, reducing the need for extensive scrolling.
Index navigation
Provides an interactive index, letting you go straight to where a term or subject appears in the text without manual searching.
Provides an interactive index, letting you go straight to where a term or subject appears in the text without manual searching.
Reading Order & Textual Equivalents
Single logical reading order
You will encounter all content (including footnotes, captions, etc.) in a clear, sequential flow, making it easier to follow with assistive tools like screen readers.
You will encounter all content (including footnotes, captions, etc.) in a clear, sequential flow, making it easier to follow with assistive tools like screen readers.
Short alternative textual descriptions
You get concise descriptions (for images, charts, or media clips), ensuring you do not miss crucial information when visual or audio elements are not accessible.
You get concise descriptions (for images, charts, or media clips), ensuring you do not miss crucial information when visual or audio elements are not accessible.