← Back to papers
2019 NAACL NAACL 2019

Frequency vs. Association for Constraint Selection in Usage-Based Construction Grammar

Abstract

AbstractA usage-based Construction Grammar (CxG) posits that slot-constraints generalize from common exemplar constructions. But what is the best model of constraint generalization? This paper evaluates competing frequency-based and association-based models across eight languages using a metric derived from the Minimum Description Length paradigm. The experiments show that association-based models produce better generalizations across all languages by a significant margin.

🌉 Interdisciplinary Bridge — Deep Learning and Interdisciplinary
🧭 Keyword Pioneer — constraint generalization
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing

Authors

Jonathan Dunn

Topics

Deep Learning > Techniques > Model Architecture Interdisciplinary > Linguistics > Computational Linguistics Interdisciplinary > Cognitive Science > Cognitive Modeling

Keywords

minimum description length construction grammar constraint generalization frequency-based model association-based model
Download PDF

Related papers

Semantic Spatial Representation: a unique representation of an environment based on an ontology for robotic applications 2019
SPARSE: Structured Prediction using Argument-Relative Structured Encoding 2019
Learning Multilingual Word Embeddings Using Image-Text Data 2019
Correlation Coefficients and Semantic Textual Similarity 2019
An Adversarial Learning Framework For A Persona-Based Multi-Turn Dialogue Model 2019