← Search

Maarten De Raedt

2 accepted papers

2022

Robustifying Sentiment Classification by Maximally Exploiting Few Counterfactuals

EMNLP 2022main

For text classification tasks, finetuned language models perform remarkably well. Yet, they tend to rely on spurious patterns in training data, thus limiting their performance on out-of-distribution (OOD) test data. Among recent models aiming to avoid this spurious pattern problem, adding extra coun…

2021

A Simple Geometric Method for Cross-Lingual Linguistic Transformations with Pre-trained Autoencoders

EMNLP 2021main

Powerful sentence encoders trained for multiple languages are on the rise. These systems are capable of embedding a wide range of linguistic properties into vector representations. While explicit probing tasks can be used to verify the presence of specific linguistic properties, it is unclear whethe…

Cited by 2SourcePDFScholar