Year: 2019
Type: conference-paper
Abstract: Recent advances in language modeling using deep neural networks have shown that these models learn representations, that vary with the network depth from morphology to semantic relationships like co-reference.We apply pre-trained language models to low-resource named entity recognition for Historic German.We show on a series of experiments that character-based pre-trained language models do not run into trouble when faced with lowresource datasets.Our pre-trained characterbased language models improve upon classical CRF-based methods and previous work on Bi-LSTMs by boosting F1 score performance by up to 6%.Our pre-trained language and NER models are publicly available 1 .
DOI: 10.18653/v1/w19-4312
Authors: Stefan Schweter, Johannes Baiter
Institution: Bavarian State Library
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2951214828