A language-vision model for translation
Author(s)
Fu, Allison.
Download1192544690-MIT.pdf (2.687Mb)
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
Boris Katz.
Terms of use
Metadata
Show full item recordAbstract
Machine translation or the automatic translation by computers from a source language to target language is a well-studied, difficult research problem. In recent years, there has been increased interest in grounding translation in vision. We introduce an unsupervised machine translation system grounded in video that can perform Chinese-English translation without the need for a parallel text corpus. In particular, we train separate Chinese and English generative language-vision models on only 267 captioned videos. We then perform translation by sampling video features for an input sentence in Chinese and finding the top-scoring English sentence or translation that describes the sampled video frames. We found that such a system picks out the correct translation with high accuracy and is a promising step towards augmenting language understanding with video.
Description
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020 Cataloged from the official PDF of thesis. Includes bibliographical references (pages 55-58).
Date issued
2020Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.