Nils Rethmeier
YOU?
Author Swipe
View article: Understanding and Analyzing Model Robustness and Knowledge-Transfer in Multilingual Neural Machine Translation using TX-Ray
Understanding and Analyzing Model Robustness and Knowledge-Transfer in Multilingual Neural Machine Translation using TX-Ray Open
Neural networks have demonstrated significant advancements in Neural Machine Translation (NMT) compared to conventional phrase-based approaches. However, Multilingual Neural Machine Translation (MNMT) in extremely low-resource settings rem…
View article: VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets
VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets Open
The anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between markets. Consequently, illegal markets and their connections are challenging to uncover on the Darknet. To iden…
View article: VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets
VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets Open
The anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between markets. Consequently, illegal markets and their connections are challenging to uncover on the Darknet. To iden…
View article: A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned, and Perspectives
A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned, and Perspectives Open
Modern natural language processing (NLP) methods employ self-supervised pretraining objectives such as masked language modeling to boost the performance of various downstream tasks. These pretraining methods are frequently extended with re…
View article: Long-Tail Zero and Few-Shot Learning via Contrastive Pretraining on and for Small Data
Long-Tail Zero and Few-Shot Learning via Contrastive Pretraining on and for Small Data Open
Preserving long-tail, minority information during model compression has been linked to algorithmic fairness considerations. However, this assumes that large models capture long-tail information and smaller ones do not, which raises two que…
View article: Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings
Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings Open
Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics. P…
View article: Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings
Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings Open
Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics. P…
View article: A Primer on Contrastive Pretraining in Language Processing: Methods,\n Lessons Learned and Perspectives
A Primer on Contrastive Pretraining in Language Processing: Methods,\n Lessons Learned and Perspectives Open
Modern natural language processing (NLP) methods employ self-supervised\npretraining objectives such as masked language modeling to boost the\nperformance of various application tasks. These pretraining methods are\nfrequently extended wit…
View article: Data-Efficient Pretraining via Contrastive Self-Supervision
Data-Efficient Pretraining via Contrastive Self-Supervision Open
For natural language processing `text-to-text' tasks, the prevailing approaches heavily rely on pretraining large self-supervised models on increasingly larger `task-external' data. Transfer learning from high-resource pretraining works we…
View article: EffiCare: Better Prognostic Models via Resource-Efficient Health Embeddings
EffiCare: Better Prognostic Models via Resource-Efficient Health Embeddings Open
Recent medical prognostic models adapted from high data-resource fields like language processing have quickly grown in complexity and size. However, since medical data typically constitute low data-resource settings, performances on tasks …
View article: EffiCare: Better Prognostic Models via Resource-Efficient Health Embeddings.
EffiCare: Better Prognostic Models via Resource-Efficient Health Embeddings. Open
Recent medical prognostic models adapted from high data-resource fields like language processing have quickly grown in complexity and size. However, since medical data typically constitute low data-resource settings, performances on tasks …
View article: TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLP
TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLP Open
While state-of-the-art NLP explainability (XAI) methods focus on explaining per-sample decisions in supervised end or probing tasks, this is insufficient to explain and quantify model knowledge transfer during (un-)supervised training. Thu…
View article: TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in\n (Un-)Supervised NLP
TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in\n (Un-)Supervised NLP Open
While state-of-the-art NLP explainability (XAI) methods focus on explaining\nper-sample decisions in supervised end or probing tasks, this is insufficient\nto explain and quantify model knowledge transfer during (un-)supervised\ntraining. …
View article: MoRTy: Unsupervised Learning of Task-specialized Word Embeddings by Autoencoding
MoRTy: Unsupervised Learning of Task-specialized Word Embeddings by Autoencoding Open
Word embeddings have undoubtedly revolutionized NLP. However, pre-trained embeddings do not always work for a specific task (or set of tasks), particularly in limited resource setups. We introduce a simple yet effective, self-supervised po…
View article: Learning Comment Controversy Prediction in Web Discussions Using Incidentally Supervised Multi-Task CNNs
Learning Comment Controversy Prediction in Web Discussions Using Incidentally Supervised Multi-Task CNNs Open
Comments on web news contain controversies that manifest as inter-group agreement-conflicts. Tracking such rapidly evolving controversy could ease conflict resolution or journalist-user interaction. However, this presupposes controversy on…
View article: Detecting Named Entities and Relations in German Clinical Reports
Detecting Named Entities and Relations in German Clinical Reports Open
Clinical notes and discharge summaries are commonly used in the clinical routine and contain patient related information such as well-being, findings and treatments. Information is often described in text form and presented in a semi-struc…
View article: Common Round: Application of Language Technologies to Large-Scale Web Debates
Common Round: Application of Language Technologies to Large-Scale Web Debates Open
Hans Uszkoreit, Aleksandra Gabryszak, Leonhard Hennig, Jörg Steffen, Renlong Ai, Stephan Busemann, Jon Dehdari, Josef van Genabith, Georg Heigold, Nils Rethmeier, Raphael Rubino, Sven Schmeier, Philippe Thomas, He Wang, Feiyu Xu. Proceedin…