105 citations · 245 across the 61 of their papers we have counts for
7 papers · 2 filters
Where exactly does contextualization in a PLM happen?
Soniya Vijayakumar, Tanja Bäumel, Simon Ostermann +1
Pre-trained Language Models (PLMs) have shown to be consistently successful in a plethora of NLP tasks due to their ability to learn contextualized representations of words (Ethaya…
Investigating the Encoding of Words in BERT's Neurons using Feature Textualization
Tanja Baeumel, Soniya Vijayakumar, Josef van Genabith +2
Pretrained language models (PLMs) form the basis of most state-of-the-art NLP technologies. Nevertheless, they are essentially black boxes: Humans do not have a clear understanding…
Translating away Translationese without Parallel Data
Rricha Jalota, Koel Dutta Chowdhury, Cristina España-Bonet +1
Translated texts exhibit systematic linguistic differences compared to original texts in the same language, and these differences are referred to as translationese. Translationese…
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…
When your Cousin has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages
Niyati Bafna, Cristina España-Bonet, Josef van Genabith +2
Most existing approaches for unsupervised bilingual lexicon induction (BLI) depend on good quality static or contextual embeddings requiring large monolingual corpora for both lang…
Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?
Sonal Sannigrahi, Josef van Genabith, Cristina Espana-Bonet
Dense vector representations for textual data are crucial in modern NLP. Word embeddings and sentence embeddings estimated from raw texts are key in achieving state-of-the-art resu…