30 citations · 225 across the 39 of their papers we have counts for
7 papers · 2 filters
Probing Multilingual BERT for Genetic and Typological Signals
Taraka Rama, Lisa Beinborn, Steffen Eger
We probe the layers in multilingual BERT (mBERT) for phylogenetic and geographic language signals across 100 languages and compute language distances based on the mBERT representat…
Vec2Sent: Probing Sentence Embeddings with Natural Language Generation
Martin Kerscher, Steffen Eger
We introspect black-box sentence embeddings by conditionally generating from them with the objective to retrieve the underlying discrete sentence. We perceive of this as a new unsu…
From Hero to Zéroe: A Benchmark of Low-Level Adversarial Attacks
Steffen Eger, Yannik Benz
Adversarial attacks are label-preserving modifications to inputs of machine learning classifiers designed to fool machines but not humans. Natural Language Processing (NLP) has mos…
Inducing Language-Agnostic Multilingual Representations
Wei Zhao, Steffen Eger, Johannes Bjerva +1
Cross-lingual representations have the potential to make NLP techniques available to the vast majority of languages in the world. However, they currently require large pretraining…
On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation
Wei Zhao, Goran Glavaš, Maxime Peyrard +3
Evaluation of cross-lingual encoders is usually performed either via zero-shot cross-lingual transfer in supervised downstream tasks or via unsupervised cross-lingual textual simil…
SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization
Yang Gao, Wei Zhao, Steffen Eger
We study unsupervised multi-document summarization evaluation metrics, which require neither human-written reference summaries nor human annotations (e.g. preferences, ratings, etc…