4 papers
Measuring Spurious Correlation in Classification: 'Clever Hans' in Translationese
Angana Borah, Daria Pylypenko, Cristina Espana-Bonet +1
Recent work has shown evidence of 'Clever Hans' behavior in high-performance neural translationese classifiers, where BERT-based classifiers capitalize on spurious correlations, in…
Explaining Translationese: why are Neural Classifiers Better and what do they Learn?
Kwabena Amponsah-Kaakyire, Daria Pylypenko, Josef van Genabith +1
Recent work has shown that neural feature- and representation-learning, e.g. BERT, achieves superior performance over traditional manual feature engineering based approaches, with…
Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification
Daria Pylypenko, Kwabena Amponsah-Kaakyire, Koel Dutta Chowdhury +2
Traditional hand-crafted linguistically-informed features have often been used for distinguishing between translated and original non-translated texts. By contrast, to date, neural…
Leveraging Neural Machine Translation for Word Alignment
Vilém Zouhar, Daria Pylypenko
The most common tools for word-alignment rely on a large amount of parallel sentences, which are then usually processed according to one of the IBM model algorithms. The training d…