In this talk, we will present ongoing efforts of Alibaba on large-scale multi-modal search ad question-answering, including image search, video search, cross lingual retrieval, and QA based on machine reading and comprehension (MRC). We will also share in this talk the core technologies that are crucial to the development of the related technologies, including representation learning, data augmentation, and robust learning.
Paper
Full text
Large-scale Multi-modal Search and QA at Alibaba
Semantic Scholar · Computer Science · 2020
Abstract
In this talk, we will present ongoing efforts of Alibaba on large-scale multi-modal search ad question-answering, including image search, video search, cross lingual retrieval, and QA based on machine reading and comprehension (MRC). We will also share in this talk the core technologies that are crucial to the development of the related technologies, including representation learning, data augmentation, and robust learning.