Følg
Letitia Parcalabescu
Letitia Parcalabescu
PhD | IPAI Aleph Alpha Research
Verifisert e-postadresse på aleph-alpha-ip.ai - Startside
Tittel
Sitert av
Sitert av
År
MAGMA--Multimodal Augmentation of Generative Models through Adapter-based Finetuning
C Eichenberg, S Black, S Weinbach, L Parcalabescu, A Frank
Findings of the Association for Computational Linguistics: EMNLP 2022, 2416 …, 2022
1122022
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
L Parcalabescu, M Cafagna, L Muradjan, A Frank, I Calixto, A Gatt
Proceedings of the 60th Annual Meeting of the Association for Computational …, 2022
1002022
Neural natural language generation: A survey on multilinguality, multimodality, controllability and learning
E Erdem, M Kuyu, S Yagcioglu, A Frank, L Parcalabescu, B Plank, A Babii, ...
Journal of Artificial Intelligence Research 73, 1131-1207, 2022
612022
Seeing past words: Testing the cross-modal capabilities of pretrained V&L models on counting tasks
L Parcalabescu, A Gatt, A Frank, I Calixto
Proceedings of the 1st Workshop on Multimodal Semantic Representations (MMSR …, 2021
53*2021
AMR similarity metrics from principles
J Opitz, L Parcalabescu, A Frank
Transactions of the Association for Computational Linguistics 8, 522-538, 2020
462020
What is Multimodality?
L Parcalabescu, N Trost, A Frank
Proceedings of the Workshop Beyond Language: Multimodal Semantic …, 2021
422021
MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks
L Parcalabescu, A Frank
Proceedings of the 61st Annual Meeting of the Association for Computational …, 2023
292023
On measuring faithfulness or self-consistency of natural language explanations
L Parcalabescu, A Frank
arXiv preprint arXiv:2311.07466, 2023
26*2023
Exploring phrase grounding without training: Contextualisation and extension to text-based image retrieval
L Parcalabescu, A Frank
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
102020
Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?
L Parcalabescu, A Frank
The Thirteenth International Conference on Learning Representations (ICLR), 2024
62024
ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
I Kesen, A Pedrotti, M Dogan, M Cafagna, EC Acikgoz, L Parcalabescu, ...
The Twelfth International Conference on Learning Representations (ICLR), 2023
62023
WEADE: A workflow for enrichment analysis and data exploration
N Trost, E Rempel, O Ermakova, S Tamirisa, L Pârcălăbescu, M Boutros, ...
Plos one 13 (9), e0204016, 2018
62018
Measuring the Contributions of Vision and Text Modalities in Multimodal Transformers
L Parcalabescu
PhD Thesis at Heidelberg University, 2024
2024
Grounding Plural Phrases: Countering Evaluation Biases by Individuation
J Suter, L Parcalabescu, A Frank
Proceedings of the Second Workshop on Advances in Language and Vision …, 2021
2021
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–14