Word learning as category formation | PLOS One

Roles Conceptualization, Formal analysis, Investigation, Methodology, Validation, Visualization, Writing – original draft, Writing – review & editing * E-mail: scaplan@gc.cuny.edu Affiliation Linguistics Program, CUNY Graduate Center, New York, New York, United States of America https://orcid.org/0000-0003-2733-8100 A fundamental question in word learning is how, given only evidence about what objects a word has previously referred to, children are able to generalize to the correct class. How does a learner end up knowing that “poodle” only picks out a specific subset of dogs rather than the broader class and vice versa? Numerous phenomena have been identified in guiding learner behavior such as the “suspicious coincidence effect” (SCE)—that an increase in the sample size of training objects facilitates more narrow (subordinate) word meanings. While SCE seems to support a class of models based in statistical infe

Word learning as category formation | PLOS One Browse Subject Areas ? Click through the PLOS taxonomy to find articles in your field. For more information about PLOS Subject Areas, click here . Article Authors Metrics Comments Media Coverage Reader Comments Figures Figures Abstract A fundamental question in word learning is how, given only evidence about what objects a word has previously referred to, children are able to generalize to the correct class. How does a learner end up knowing that “poodle” only picks out a specific subset of dogs rather than the broader class and vice versa? Numero

related reading

• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• Grounded language acquisition through the eyes and ears of a single childstatic.us.edusercontent.com
• Learning to Merge Word Sensesaclanthology.org
• Subliminal Learning: Language Models Transmit Behavioral Traits via Hidden Signals in Dataalignment.anthropic.com
• To Understand Language is to Understand Generalization | Eric Jangevjang.com
• [2009.01719] Grounded Language Learning Fast and Slowarxiv.org
• Do Machine Learning Models Memorize or Generalize?pair.withgoogle.com
• Base Models Know How to Reason, Thinking Models Learn Whenarxiv.org
• Specificity ratings for English datalink.springer.com
• How does in-context learning work? A framework for understanding the differences from traditional supervised learning | SAIL Blogai.stanford.edu
• [2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org
• Sophie Wangsophielwang.com