3 papers
cs.CL2024
Do Vision and Language Models Share Concepts? A Vector Space Alignment Study
Jiaang Li, Yova Kementchedjhieva, Constanza Fierro +1
Large-scale pretrained language models (LMs) are said to ``lack the ability to connect utterances to the world'' (Bender and Koller, 2020), because they do not have ``mental models…
cs.CL2024
WebQAmGaze: A Multilingual Webcam Eye-Tracking-While-Reading Dataset
Tiago Ribeiro, Stephanie Brandl, Anders Søgaard +1
We present WebQAmGaze, a multilingual low-cost eye-tracking-while-reading dataset, designed as the first webcam-based eye-tracking corpus of reading to support the development of e…
cs.CL2024
A Discriminative Latent-Variable Model for Bilingual Lexicon Induction
Sebastian Ruder, Ryan Cotterell, Yova Kementchedjhieva +2
We introduce a novel discriminative latent variable model for bilingual lexicon induction. Our model combines the bipartite matching dictionary prior of Haghighi et al. (2008) with…