activity
20192021
most citedNLNDE: The Neither-Language-Nor-Domain-Experts' Way of Spanish Medical Document De-Identification

11 citations · 11 across the 4 of their papers we have counts for

collaborators

11 papers

cs.CL2021

Boosting Transformers for Job Expression Extraction and Classification in a Low-Resource Setting

Lukas Lange, Heike Adel, Jannik Strötgen

In this paper, we explore possible improvements of transformer models in a low-resource setting. In particular, we present our approaches to tackle the first two of three subtasks…

cs.CL2021

Enriched Attention for Robust Relation Extraction

Heike Adel, Jannik Strötgen

The performance of relation extraction models has increased considerably with the rise of neural networks. However, a key issue of neural relation extraction is robustness: the mod…

cs.CL2021

To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning

Lukas Lange, Jannik Strötgen, Heike Adel +1

In low-resource settings, model transfer can help to overcome a lack of labeled data for many tasks and domains. However, predicting useful transfer sources is a challenging proble…

cs.CL2020

NLNDE at CANTEMIST: Neural Sequence Labeling and Parsing Approaches for Clinical Concept Extraction

Lukas Lange, Xiang Dai, Heike Adel +1

The recognition and normalization of clinical information, such as tumor morphology mentions, is an important, but complex process consisting of multiple subtasks. In this paper, w…

cs.CL2020

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios

Michael A. Hedderich, Lukas Lange, Heike Adel +2

Deep neural networks and huge language models are becoming omnipresent in natural language applications. As they are known for requiring large amounts of training data, there is a…

cs.CL2020

FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations

Lukas Lange, Heike Adel, Jannik Strötgen +1

Combining several embeddings typically improves performance in downstream tasks as different embeddings encode different information. It has been shown that even models using embed…