Skip to main content
SpringerLink
Log in
Book cover
  • Book
  • © 2024

Cognitive Plausibility in Natural Language Processing

Authors:

  1. Lisa Beinborn

    1. Faculty of Humanities, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands

    View author publications

    You can also search for this author in PubMed   Google Scholar

  2. Nora Hollenstein

    1. Department of Nordic Studies and Linguistics, University of Copenhagen, Copenhagen, Denmark

    View author publications

    You can also search for this author in PubMed   Google Scholar

  • Provides a resource for students and researchers in natural language processing, machine learning, and cognitive science

  • Argues that model development targeted purely toward performance-driven evaluation has reached a ceiling

  • Approaches the topic by focusing on behavioral patterns, representational structure, and procedural strategies

Part of the book series: Synthesis Lectures on Human Language Technologies (SLHLT)

  • 197 Accesses

Sections

Buy it now

eBook USD 34.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book USD 44.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

This is a preview of subscription content, access via your institution.

Table of contents (7 chapters)

  1. Front Matter

    Pages i-xi
    PDF

  2. Introduction

    • Lisa Beinborn, Nora Hollenstein
    Pages 1-10

  3. Foundations of Language Modeling

    • Lisa Beinborn, Nora Hollenstein
    Pages 11-29

  4. Cognitive Signals of Language Processing

    • Lisa Beinborn, Nora Hollenstein
    Pages 31-60

  5. Behavioral Patterns

    • Lisa Beinborn, Nora Hollenstein
    Pages 61-88

  6. Representational Structure

    • Lisa Beinborn, Nora Hollenstein
    Pages 89-119

  7. Procedural Strategies

    • Lisa Beinborn, Nora Hollenstein
    Pages 121-151

  8. Towards Cognitively More Plausible Models

    • Lisa Beinborn, Nora Hollenstein
    Pages 153-158
Back to top

About this book

This book explores the cognitive plausibility of computational language models and why it’s an important factor in their development and evaluation. The authors present the idea that more can be learned about cognitive plausibility of computational language models by linking signals of cognitive processing load in humans to interpretability methods that allow for exploration of the hidden mechanisms of neural models. The book identifies limitations when applying the existing methodology for representational analyses to contextualized settings and critiques the current emphasis on form over more grounded approaches to modeling language. The authors discuss how novel techniques for transfer and curriculum learning could lead to cognitively more plausible generalization capabilities in models. The book also highlights the importance of instance-level evaluation and includes thorough discussion of the ethical considerations that may arise throughout the various stages of cognitive plausibility research. 
Back to top

Keywords

  • Cognitive Plausibility
  • Interpretability
  • Cognitive Signals
  • Language Models
  • Natural Language Processing
  • Machine Learning
Back to top

Authors and Affiliations

  • Faculty of Humanities, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands

    Lisa Beinborn

  • Department of Nordic Studies and Linguistics, University of Copenhagen, Copenhagen, Denmark

    Nora Hollenstein

Back to top

About the authors

Lisa Beinborn is an Assistant Professor for Natural Language Processing at the Computational Linguistics and Text Mining Lab at Vrije Universiteit Amsterdam. She studied Computational Linguistics in Saarbrücken, Barcelona, and Bolzano, and obtained her PhD in Computer Science at TU Darmstadt. Her research focuses on cognitively plausible language processing and cross-lingual models. She works on the interpretability of representational transfer and is interested in educational applications of NLP.

Nora Hollenstein is currently working at the Center for Language Technology of the University of Copenhagen and at the Department of Computational Linguistics of the University of Zurich. She obtained her PhD from ETH Zurich working on cognitively inspired NLP. The focus of her research lies in improving and evaluating natural language processing applications with cognitive signals such as eye-tracking and brain activity recordings. She is especially interested in multilingual and multimodal NLP
Back to top

Bibliographic Information

Back to top
Access via your institution

Buy it now

eBook USD 34.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book USD 44.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

search

Navigation