Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from EDBT 2026 / reviewers in the wild / expert

Niels van der Heijden

dblp:255/6226 · DBLP profile ↗
← Back
3ranked-venue papers
3as first author
2since 2021 · last 2023
0009-0005-0632-8327ORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 3 · 3 first-author · 2 since 2021Graphics, computer vision, multimedia, augmented reality and games · 1 · 1 first-author

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Representation and self-supervised learning · 33% Language models and text generation · 33% Transfer learning and domain adaptation · 33%

Topics — the 3 heaviest of 3, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Natural language and speech › Language models and text generation › multilingual language models
multilingual contextual embeddings		 0.412020
A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings · AAAI 2020
Machine learning › Representation and self-supervised learning › word representation
word embedding		 0.412020
A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings · AAAI 2020
Machine learning › Transfer learning and domain adaptation
zero-shot transfer		 0.412020
A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings · AAAI 2020

Methods — techniques the papers use, named apart from their topics

pre-training · 0.4joint training · 0.4
YearPublicationVenuePosition
2023 K-hop neighbourhood regularization for few-shot learning on graphs: A case study of text classification
abstract
We present FewShotTextGCN, a novel method designed to effectively utilize the properties of word-document graphs for improved learning in low-resource settings.We introduce Khop Neighborhood Regularization, a regularizer for heterogeneous graphs, and show that it stabilizes and improves learning when only a few training samples are available.We furthermore propose a simplification in the graphconstruction method, which results in a graph that is ∼7 times less dense and yields better performance in low-resource settings while performing on-par with the state of the art in highresource settings.Finally, we introduce a new variant of Adaptive Pseudo-Labeling tailored for word-document graphs.When using as little as 20 samples for training, we outperform a strong TextGCN baseline with 17% in absolute accuracy on average over eight languages.We demonstrate that our method can be applied to document classification without any language model pretraining on a wide range of typologically diverse languages while performing on par with large pretrained language models.
Niels van der Heijden, Ekaterina Shutova, Helen Yannakoudakis
 EACL1
2021 Multilingual and cross-lingual document classification: A meta-learning approach
abstract
Niels van der Heijden, Helen Yannakoudakis, Pushkar Mishra, Ekaterina Shutova. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.
Niels van der Heijden, Helen Yannakoudakis, Pushkar Mishra, Ekaterina Shutova
 EACL1
2020 A Comparison of Architectures and Pretraining Methods for Contextualized Multilingual Word Embeddings
abstract
The lack of annotated data in many languages is a well-known challenge within the field of multilingual natural language processing (NLP). Therefore, many recent studies focus on zero-shot transfer learning and joint training across languages to overcome data scarcity for low-resource languages. In this work we (i) perform a comprehensive comparison of state-of-the-art multilingual word and sentence encoders on the tasks of named entity recognition (NER) and part of speech (POS) tagging; and (ii) propose a new method for creating multilingual contextualized word embeddings, compare it to multiple baselines and show that it performs at or above state-of-the-art level in zero-shot transfer settings. Finally, we show that our method allows for better knowledge sharing across languages in a joint training setting.
Niels van der Heijden, Samira Abnar, Ekaterina Shutova
 AAAI1