3 papers
cs.CL2022
Task-Specific Embeddings for Ante-Hoc Explainable Text Classification
Kishaloy Halder, Josip Krapac, Alan Akbik +2
Current state-of-the-art approaches to text classification typically leverage BERT-style Transformer models with a softmax classifier, jointly fine-tuned to predict class labels of…
cs.CL2020
FLERT: Document-Level Features for Named Entity Recognition
Stefan Schweter, Alan Akbik
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 crosses sentence boundar…
cs.CL2018
Syntax-Aware Language Modeling with Recurrent Neural Networks
Duncan Blythe, Alan Akbik, Roland Vollgraf
Neural language models (LMs) are typically trained using only lexical features, such as surface forms of words. In this paper, we argue this deprives the LM of crucial syntactic si…