Stress Rules from Surface Forms: Experiments with Program Synthesis
Learning linguistic generalizations from only a few examples is a challenging task. Recent work has shown that program synthesis – a method to learn rules from data in the form of programs in a domain-specific language – can be used to learn phonological rules in highly data-constrained settings. In this paper, we use the problem of phonological stress placement as a case to study how the design of the domain-specific language influences the generalization ability when using the same learning algorithm. We find that encoding the distinction between consonants and vowels results in much better performance, and providing syllable-level information further improves generalization. Program synthesis, thus, provides a way to investigate how access to explicit linguistic information influences what can be learnt from a small number of examples.
Code (0)
등록된 구현이 없습니다.
Tasks
Program SynthesisSimilar Papers 제목 키워드 기반
LLMs Lean on Priors, Not Programming Language Semantics
Recent work asks whether large language models (LLMs) condition their reasoning on explicit rules rather than statistical regularities from pretraining. Program execution provides a canonical instance: formal semantics d…
Digital Image-Based Stress–Permeability Relationships of Rough Fractures Using Numerical Contact Mechanics and Stokes Equation
Flow in fractures is sensitive to their geometrical surface characteristics. The surface can undergo deformation if there is a change in stress. Natural fractures have complex geometries and rough surfaces which complica…
Contact mechanicsTensiStrength: Stress and relaxation magnitude detection for social media texts
Computer systems need to be able to react to stress in order to perform optimally on some tasks. This article describes TensiStrength, a system to detect the strength of stress and relaxation expressed in social media te…
BIG-bench Machine LearningSentiment AnalysisLinear correlation between active and resistive stresses informs on force generation and stress transmission in adherent cells
Animal cells are active, contractile objects. While bioassays address the molecular characterization of cell contractility, the mechanical characterization of the active forces in cells remains challenging. Here by confr…
Depth-Resolved Coral Reef Thermal Fields from Satellite SST and Sparse In-Situ Loggers Using Physics-Informed Neural Networks
Satellite sea surface temperature (SST) products underpin global coral bleaching monitoring, yet they measure only the ocean skin. Corals inhabit depths from the shallows to beyond 20 metres, where temperatures can be 1-…