Nikolai Ilinykh — accepted AI-conference papers

2023

Describe Me an Auklet: Generating Grounded Perceptual Category Descriptions

EMNLP 2023long main

Human speakers can generate descriptions of perceptual concepts, abstracted from the instance-level. Moreover, such descriptions can be used by other speakers to learn provisional representations of those concepts. Learning and using abstract perceptual concepts is under-investigated in the language…

Cited by 0 Source ↗Scholar ↗

2022

Attention as Grounding: Exploring Textual and Cross-Modal Attention on Entities and Relations in Language-and-Vision Transformer

Nikolai Ilinykh, Simon Dobnik

ACL 2022findings

We explore how a multi-modal transformer trained for generation of longer image descriptions learns syntactic and semantic representations about entities and relations grounded in objects at the level of masked self-attention (text generation) and cross-modal attention (information fusion). We obser…

Cited by 18 Source ↗PDF ↗code ↗Scholar ↗