2019
ACL
ACL 2019
Semantic Expressive Capacity with Bounded Memory
Abstract
AbstractWe investigate the capacity of mechanisms for compositional semantic parsing to describe relations between sentences and semantic representations. We prove that in order to represent certain relations, mechanisms which are syntactically projective must be able to remember an unbounded number of locations in the semantic representations, where nonprojective mechanisms need not. This is the first result of this kind, and has consequences both for grammar-based and for neural systems.
🌉
Interdisciplinary Bridge
— Artificial Intelligence and Interdisciplinary and Knowledge & Reasoning and Machine Learning and Natural Language Processing
🧭
Keyword Pioneer
— expressive capacity
🐝
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, Robotics, Security & Privacy, Speech & Audio
Authors
Topics
Machine Learning > Optimization & Theory > Learning Theory
Natural Language Processing > Understanding > Semantic Analysis
Knowledge & Reasoning > Reasoning > Formal Methods
Interdisciplinary > Linguistics > Semantics
Machine Learning > Learning Types > Representation Learning
Artificial Intelligence > Core AI > Reasoning
Natural Language Processing > Applications > Semantic Analysis