Showing cs.CLShow all
3 papers · 1 filter
cs.CL2024
CV-Probes: Studying the interplay of lexical and world knowledge in visually grounded verb understanding
Ivana Beňová, Michal Gregor, Albert Gatt
How do vision-language (VL) transformer models ground verb phrases and do they integrate contextual and world knowledge in this process? We introduce the CV-Probes dataset, contain…
cs.CL2024
Multilingual Models for Check-Worthy Social Media Posts Detection
Sebastian Kula
This work presents an extensive study of transformer-based NLP models application for detection of social media posts that contain verifiable factual claims and harmful claims. The…
cs.CL2024
Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided Masking
Ivana Beňová, Jana Košecká, Michal Gregor +3
The dominant probing approaches rely on the zero-shot performance of image-text matching tasks to gain a finer-grained understanding of the representations learned by recent multim…