Papers by Jochen De Weerdt

4 papers
Language Fusion for Parameter-Efficient Cross-lingual Transfer (2025.acl-long)

Copied to clipboard

Challenge: Limited availability of multilingual text corpora for pretraining results in poor performance on downstream tasks due to undertrained representation spaces for languages other than English.
Approach: They propose a method that integrates source and target language representations within low-rank (LoRA) adapters using lightweight linear transformations to enhance representation quality and transfer performance for languages other than English.
Outcome: The proposed method improves representation quality and performance for languages other than English while maintaining parameter efficiency.
CORE: A Few-Shot Company Relation Classification Dataset for Robust Domain Adaptation. (2023.emnlp-main)

Copied to clipboard

Challenge: Existing datasets that focus on company relations and business entities are lacking in relation classification.
Approach: They introduce a few-shot relation classification dataset for company relations and business entities . they use a dataset that includes 4,708 instances of 12 relation types .
Outcome: The proposed dataset includes 4,708 instances of 12 relation types with corresponding textual evidence extracted from company Wikipedia pages.
Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation Learning (2024.naacl-short)

Copied to clipboard

Challenge: Relation classification (RC) models extract rich information from sentences with limited labeled instances.
Approach: They propose to combine multiple sentence representations with contrastive learning to enhance information extraction by combining multiple sentence and entity tokens.
Outcome: The proposed approach is able to extract discriminative information from multiple representations and contrastive learning.
Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques (2023.emnlp-main)

Copied to clipboard

Challenge: Debiasing techniques that target sentence representations are being investigated in multilingual models . a growing interest in addressing bias detection and mitigation in NLP due to their societal implications.
Approach: They examine the transferability of debiasing techniques across different languages within multilingual models by using a dataset from CrowS-Pairs.
Outcome: The proposed techniques reduce bias in English, French, German, and Dutch by 13% . the authors also show that the techniques with additional pretraining exhibit enhanced cross-lingual effectiveness for the languages included in the analyses .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations