Papers by Sarah Ruth Brogden Payne

2 papers
Exploring Linguistic Probes for Morphological Inflection (2023.emnlp-main)

Copied to clipboard

Challenge: morphological inflection models typically employ language-independent data splitting algorithms.
Approach: They propose language-specific probes to test aspects of morphological generalization . they use three morphology-distinct languages to test their generalization abilities .
Outcome: The proposed language-specific probes are used to test morphological generalization abilities on three distinct languages.
Lemmas Matter, But Not Like That: Predictors of Lemma-Based Generalization in Morphological Inflection (2025.findings-acl)

Copied to clipboard

Challenge: Recent work suggests that lemma overlap drives model performance on morphological inflection tasks, but the impact of lemmm overlap is debated.
Approach: They propose a novel algorithm to investigate predictors of accuracy on seen and unseen lemmas by combining the number of lema in train with the number in train.
Outcome: The proposed algorithm shows that the number of lemmas in train has a stronger effect on accuracy on unseen than seen lemmes.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations