4 papers · 1 filter
Testing the Assumptions of Active Learning for Translation Tasks with Few Samples
Lorenzo Jaime Yu Flores, Cesare Spinoso di-Piano, Ori Ernst +2
Active learning (AL) is a training paradigm for selecting unlabeled samples for annotation to improve model performance on a test set, which is useful when only a limited number of…
Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
Lorenzo Jaime Yu Flores, Cesare Spinoso di-Piano, Jackie Chi Kit Cheung
Uncertainty quantification is a set of techniques that measure confidence in language models. They can be used, for example, to detect hallucinations or alert users to review uncer…
Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing
Behzad Shayegh, Hobie H. -B. Lee, Xiaodan Zhu +2
We address unsupervised dependency parsing by building an ensemble of diverse existing models through post hoc aggregation of their output dependency parse structures. We observe t…
Ensemble Distillation for Unsupervised Constituency Parsing
Behzad Shayegh, Yanshuai Cao, Xiaodan Zhu +2
We investigate the unsupervised constituency parsing task, which organizes words and phrases of a sentence into a hierarchical structure without using linguistically annotated data…