2025
ACL
ACL 2025
What does memory retrieval leave on the table? Modelling the Cost of Semi-Compositionality with MINERVA2 and sBERT
Abstract
AbstractDespite being ubiquitous in natural language, collocations (e.g., kick+habit) incur a unique processing cost, compared to compositional phrases (kick+door) and idioms (kick+bucket). We confirm this cost with behavioural data as well as MINERVA2, a memory model, suggesting that collocations constitute a distinct linguistic category. While the model fails to fully capture the observed human processing patterns, we find that below a specific item frequency threshold, the model’s retrieval failures align with human reaction times across conditions. This suggests an alternative processing mechanism that activates when memory retrieval fails.
❓
The Questioner
🌉
Interdisciplinary Bridge
— Artificial Intelligence and Interdisciplinary and Machine Learning and Natural Language Processing
🧭
Keyword Pioneer
— collocation processing
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Security & Privacy, Speech & Audio
Authors
Topics
Artificial Intelligence > Core AI > Memory
Machine Learning > Core Methods > Representation Learning
Natural Language Processing > Understanding > Semantic Analysis
Interdisciplinary > Linguistics > Computational Linguistics
Interdisciplinary > Cognitive Science > Cognitive Modeling
Natural Language Processing > Applications > Natural Language Inference
Natural Language Processing > Applications > Semantic Analysis