Text encoders bottleneck compositionality in contrastive vision-language models

Text encoders bottleneck compositionality in contrastive vision-language models Amita Kamath author Jack Hessel author Kai-Wei Chang author 2023-12 text Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing Houda Bouamor editor Juan Pino editor Kalika Bali editor Association for Computational Linguistics Singapore conference publication kamath-etal-2023-text 10.18653/v1/2023.emnlp-main.301 https://aclanthology.org/2023.emnlp-main.301/ 2023-12 4933 4944