Search Results for author:
Found 2 papers, 2 papers with code
Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization
We present Expected Statistic Regularization (ESR), a novel regularization technique that utilizes low-order multi-task structural statistics to shape model distributions for semi-supervised learning on low-resource datasets.
Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss
We study learning named entity recognizers in the presence of missing entity annotations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
