Were We There Already? Applying Minimal Generalization to the SIGMORPHON-UniMorph Shared Task on Cognitively Plausible Morphological Inflection
Morphological rules with various levels of specificity can be learned from example lexemes by recursive application of minimal generalization (Albright and Hayes, 2002, 2003). A model that learns rules solely through minimal generalization was used to predict average human wug-test ratings from German, English, and Dutch in the SIGMORPHON-UniMorph 2021 Shared Task, with competitive results. Some formal properties of the minimal generalization operation were proved. An automatic method was developed to create wug-test stimuli for future experiments that investigate whether the model’s morphological generalizations are too minimal.
Code (0)
등록된 구현이 없습니다.
Tasks
Morphological InflectionSpecificitySimilar Papers 제목 키워드 기반
Beyond Random Split for Assessing Statistical Model Performance
Even though a train/test split of the dataset randomly performed is a common practice, could not always be the best approach for estimating performance generalization under some scenarios. The fact is that the usual mach…
modelGeneralization to Out-of-Distribution transformations
Humans understand a set of canonical geometric transformations (such as translation, rotation and scaling) that support generalization by being untethered to any specific object. We explored inductive biases that allowed…
DiversityTranslationAdaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve?
In the last decade, the generalization and adaptation abilities of deep learning models were typically evaluated on fixed training and test distributions. Contrary to traditional deep learning, large language models (LLM…
Deep LearningNotes on data-driven output-feedback control of linear MIMO systems
Recent works have approached the data-driven design of dynamic output-feedback controllers for discrete-time LTI systems by constructing non-minimal state vectors composed of past inputs and outputs. Depending on the sys…
Safety as Computation: Certified Answer Reuse via Capability Closure in Task-Oriented Dialogue
We introduce a new paradigm for task-oriented dialogue systems: safety certification as a computational primitive for answer reuse. Current systems treat each turn independently, recomputing answers via retrieval or gene…
Task-Oriented Dialogue Systems