76 citations · 106 across the 17 of their papers we have counts for
4 papers · 1 filter
A Dataset and Strong Baselines for Classification of Czech News Texts
Hynek Kydlíček, Jindřich Libovický
Pre-trained models for Czech Natural Language Processing are often evaluated on purely linguistic tasks (POS tagging, parsing, NER) and relatively simple classification tasks such…
Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity
Katharina Hämmerl, Alina Fastowski, Jindřich Libovický +1
Previous work has shown that the representations output by contextual language models are more anisotropic than static type embeddings, and typically display outlier dimensions. Th…
Probing the Role of Positional Information in Vision-Language Models
Philipp J. Rösch, Jindřich Libovický
In most Vision-Language models (VL), the understanding of the image structure is enabled by injecting the position information (PI) about objects in the image. In our case study of…
Is a Prestigious Job the same as a Prestigious Country? A Case Study on Multilingual Sentence Embeddings and European Countries
Jindřich Libovický
We study how multilingual sentence representations capture European countries and occupations and how this differs across European languages. We prompt the models with templated se…