Jun 14, 2023 · World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models. Authors:Ziqiao Ma, Jiayi Pan, Joyce Chai.

While humans demonstrate fast mapping in new word learning, it remains unclear whether modern vision-language models can truly represent language with their ...

Official Code for ACL 2023 Outstanding Paper: World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models ...

World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models ... world language learning through Grounded Open Vocabulary ...

This work proposes World-to-Words (W2W), a novel visually-grounded language model by pre-training on image-text pairs highlighting grounding as an objective ...

Jun 14, 2023 · World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models ... The ability to connect language units to ...

Jul 7, 2023 · World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models. Ziqiao Ma, Jiayi Pan, and Joyce Chai.

Jul 12, 2023 · World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models ... Actively Supervised Clustering for Open ...

Jun 14, 2023 · Our empirical results show that learning to map words to their referents plays a significant role in grounded word acquisition.