Search Results for author:
Found 5 papers, 4 papers with code
XPASC: Measuring Generalization in Weak Supervision by Explainability and Association
To verify this assumption, we introduce a novel method, XPASC (eXPlainability-Association SCore), for measuring the generalization of a model trained with a weakly supervised dataset.
hmBERT: Historical Multilingual Language Models for Named Entity Recognition
We circumvent the need for large amounts of labeled data by using unlabeled data for pretraining a language model.
KnowMAN: Weakly Supervised Multinomial Adversarial Networks
The knowledge is captured in labeling functions, which detect certain regularities or patterns in the training samples and annotate corresponding labels for training.
Data Centric Domain Adaptation for Historical Text with OCR Errors
We propose new methods for in-domain and cross-domain Named Entity Recognition (NER) on historical data for Dutch and French.
Domain adaptation for part-of-speech tagging of noisy user-generated text
We propose an architecture that trains an out-of-domain model on a large newswire corpus, and transfers those weights by using them as a prior for a model trained on the target domain (a data-set of German Tweets) for which there is very little an-notations available.
