Search Results - "Strötgen, Jannik"

Multilingual and cross-domain temporal tagging by Strötgen, Jannik, Gertz, Michael

“…Extraction and normalization of temporal expressions from documents are important steps towards deep text understanding and a prerequisite for many NLP tasks…”
Get full text

CLIN-X: pre-trained language models and a study on cross-task transfer for concept extraction in the clinical domain by Lange, Lukas, Adel, Heike, Strötgen, Jannik, Klakow, Dietrich

“…Abstract Motivation The field of natural language processing (NLP) has recently seen a large change toward using pre-trained language models for solving almost…”
Get full text

Time and information retrieval: Introduction to the special issue by Derczynski, Leon, Strötgen, Jannik, Campos, Ricardo, Alonso, Omar

Get full text

Enriched Attention for Robust Relation Extraction by Adel, Heike, Strötgen, Jannik

“…The performance of relation extraction models has increased considerably with the rise of neural networks. However, a key issue of neural relation extraction…”
Get full text

Discourse-Aware In-Context Learning for Temporal Expression Normalization by Gautam, Akash Kumar, Lange, Lukas, Strötgen, Jannik

“…Temporal expression (TE) normalization is a well-studied problem. However, the predominately used rule-based systems are highly restricted to specific…”
Get full text

TADA: Efficient Task-Agnostic Domain Adaptation for Transformers by Hung, Chia-Chien, Lange, Lukas, Strötgen, Jannik

“…Intermediate training of pre-trained transformer-based language models on domain-specific data leads to substantial gains for downstream tasks. To increase…”
Get full text

Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization by Wang, Mingyang, Lange, Lukas, Adel, Heike, Strötgen, Jannik, Schütze, Hinrich

“…To ensure large language models contain up-to-date knowledge, they need to be updated regularly. However, model editing is challenging as it might also affect…”
Get full text

Learn it or Leave it: Module Composition and Pruning for Continual Learning by Wang, Mingyang, Adel, Heike, Lange, Lukas, Strötgen, Jannik, Schütze, Hinrich

“…In real-world environments, continual learning is essential for machine learning models, as they need to acquire new knowledge incrementally without forgetting…”
Get full text

Rehearsal-Free Modular and Compositional Continual Learning for Language Models by Wang, Mingyang, Adel, Heike, Lange, Lukas, Strötgen, Jannik, Schütze, Hinrich

“…Continual learning aims at incrementally acquiring new knowledge while not forgetting existing knowledge. To overcome catastrophic forgetting, methods are…”
Get full text

GradSim: Gradient-Based Language Grouping for Effective Multilingual Training by Wang, Mingyang, Adel, Heike, Lange, Lukas, Strötgen, Jannik, Schütze, Hinrich

“…Most languages of the world pose low-resource challenges to natural language processing models. With multilingual training, knowledge can be shared among…”
Get full text

Boosting Transformers for Job Expression Extraction and Classification in a Low-Resource Setting by Lange, Lukas, Adel, Heike, Strötgen, Jannik

“…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…”
Get full text

NLNDE at SemEval-2023 Task 12: Adaptive Pretraining and Source Language Selection for Low-Resource Multilingual Sentiment Analysis by Wang, Mingyang, Adel, Heike, Lange, Lukas, Strötgen, Jannik, Schütze, Hinrich

“…This paper describes our system developed for the SemEval-2023 Task 12 "Sentiment Analysis for Low-resource African Languages using Twitter Dataset". Sentiment…”
Get full text

Multilingual Normalization of Temporal Expressions with Masked Language Models by Lange, Lukas, Strötgen, Jannik, Adel, Heike, Klakow, Dietrich

“…The detection and normalization of temporal expressions is an important task and preprocessing step for many applications. However, prior work on normalization…”
Get full text

CLIN-X: pre-trained language models and a study on cross-task transfer for concept extraction in the clinical domain by Lange, Lukas, Adel, Heike, Strötgen, Jannik, Klakow, Dietrich

“…The field of natural language processing (NLP) has recently seen a large change towards using pre-trained language models for solving almost any task. Despite…”
Get full text

NLNDE: The Neither-Language-Nor-Domain-Experts' Way of Spanish Medical Document De-Identification by Lange, Lukas, Adel, Heike, Strötgen, Jannik

“…Natural language processing has huge potential in the medical domain which recently led to a lot of research in this field. However, a prerequisite of secure…”
Get full text

NLNDE: Enhancing Neural Sequence Taggers with Attention and Noisy Channel for Robust Pharmacological Entity Detection by Lange, Lukas, Adel, Heike, Strötgen, Jannik

“…Named entity recognition has been extensively studied on English news texts. However, the transfer to other domains and languages is still a challenging…”
Get full text

Closing the Gap: Joint De-Identification and Concept Extraction in the Clinical Domain by Lange, Lukas, Adel, Heike, Strötgen, Jannik

“…Exploiting natural language processing in the clinical domain requires de-identification, i.e., anonymization of personal information in texts. However,…”
Get full text

On the Choice of Auxiliary Languages for Improved Sequence Tagging by Lange, Lukas, Adel, Heike, Strötgen, Jannik

“…Recent work showed that embeddings from related languages can improve the performance of sequence tagging, even for monolingual models. In this analysis paper,…”
Get full text

To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning by Lange, Lukas, Strötgen, Jannik, Adel, Heike, Klakow, Dietrich

“…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…”
Get full text

FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations by Lange, Lukas, Adel, Heike, Strötgen, Jannik, Klakow, Dietrich

“…Combining several embeddings typically improves performance in downstream tasks as different embeddings encode different information. It has been shown that…”
Get full text