Search Results - "Schweter, Stefan"
-
1
FLERT: Document-Level Features for Named Entity Recognition
Published 13-11-2020“…Current state-of-the-art approaches for named entity recognition (NER) typically consider text at the sentence-level and thus do not model information that…”
Get full text
Journal Article -
2
Towards Robust Named Entity Recognition for Historic German
Published 18-06-2019“…Recent advances in language modeling using deep neural networks have shown that these models learn representations, that vary with the network depth from…”
Get full text
Journal Article -
3
German's Next Language Model
Published 21-10-2020“…In this work we present the experiments which lead to the creation of our BERT and ELECTRA based German language models, GBERT and GELECTRA. By varying the…”
Get full text
Journal Article -
4
hmBERT: Historical Multilingual Language Models for Named Entity Recognition
Published 31-05-2022“…Compared to standard Named Entity Recognition (NER), identifying persons, locations, and organizations in historical texts constitutes a big challenge. To…”
Get full text
Journal Article -
5
Data Centric Domain Adaptation for Historical Text with OCR Errors
Published 02-07-2021“…We propose new methods for in-domain and cross-domain Named Entity Recognition (NER) on historical data for Dutch and French. For the cross-domain case, we…”
Get full text
Journal Article -
6
Entities, Dates, and Languages: Zero-Shot on Historical Texts with T0
Published 11-04-2022“…In this work, we explore whether the recently demonstrated zero-shot abilities of the T0 model extend to Named Entity Recognition for out-of-distribution…”
Get full text
Journal Article -
7
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Published 09-11-2022“…Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these…”
Get full text
Journal Article