CLASP's repositories
multifracas
Multilingual FraCaS testsuite
dialogue-systems-1-2024
LT2216/LT2816 V24 Dialogsystem
language-and-perception
Situated Language and Perception Research Group
attention-as-grounding
A public repository with data and code for ''Attention as Grounding: Exploring Textual and Cross-Modal Attention on Entities and Relations in Language-and-Vision Transformer'' by Nikolai Ilinykh and Simon Dobnik. Findings of ACL, 2022.
embodied-qa
A hub repository for experiments on Embodied Question Answering
GU-CLASP.github.io
CLASP webpages
unitary-recurrent-network
Code and material for Unitary Recurrent Network language models
Bayesian-Inference-Semantics-for-Natural-Language
Source code accompanying Bayesian Inference Semantics for Natural Language
chattool-telegram
Dialogue Experimental Toolkit (DiET)
describe-me-an-auklet
A public repository with data and code for ''Describe Me an Auklet: Generating Grounded Perceptual Category Descriptions'', Bill Noble and Nikolai Ilinykh. 2023. EMNLP 2023, Main, December 6–10, Singapore.
discourse-and-decodings
A public repository with data and code for ''On Decoding and Discourse Structure in Multi-Modal Text Generation'', Nikolai Ilinykh and Simon Dobnik. Generation, Evaluation & Metrics (GEM) workshop at EMNLP, 2022.
hallucinate-or-ground
A public repository with code and experiments for ''Hallucinate or ground: how general or specific are objects descriptions generated by a vision-and-language transformer?'', Nikolai Ilinykh and Simon Dobnik. Swedish Language Technology Conference, Stockholm, 23 - 25 November, 2022.
object-naming-in-context
A public repository with data and code for ''Context matters: evaluation of target and context features on variation of object naming'', Nikolai Ilinykh and Simon Dobnik. 2023. Linguistic Insights from and for Multimodal Language Processing (LIMO), co-located with KONVENS2023, September 18-22, Ingolstadt, Germany.
opencv_zoo
Model Zoo For OpenCV DNN and Benchmarks.
what-does-a-language-and-vision-transformer-see
A public repository with data and code for ''What Does a Language-And-Vision Transformer See: The Impact of Semantic Information on Visual Representations'' by Nikolai Ilinykh and Simon Dobnik. Frontiers in Artificial Intelligence, Language and Computation. 2021.
when-an-image-tells-a-story
A public repository with data and code for ''When an Image Tells a Story: The Role of Visual and Semantic Information for Generating Paragraph Descriptions'', Nikolai Ilinykh and Simon Dobnik. 2020. In Proceedings of the 13th International Conference on Natural Language Generation, pages 338–348, Dublin, Ireland.