Grounded semantic parsing using captioned videos

We develop a semantic parser which is trained in a grounded setting using pairs of videos captioned with sentences. This setting is both data-efficient requiring little annotation and far more similar to the experience of children where they observe their environment and listen to speakers. The semantic parser recovers the meaning of English sentences despite not having access to any annotated sentences and despite the ambiguity inherent in vision where a sentence may refer to any combination of objects, object properties, relations or actions taken by any agent in a video. We introduce a new corpus for grounded language acquisition. Learning to understand language, turn sentences into logical forms, by using captioned video will significantly expand the range of data that parsers can be trained on, lower the effort of training a semantic parser, and ultimately lead to a better understanding of child language acquisition.

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2018

Author dc:creator

• Ross, Candace Cheronda

Advisor dc:contributor.advisor

• Boris Katz.

• Electrical Engineering and Computer Science.

Statement dc:rights

• MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

http://hdl.handle.net/1721.1/118036

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/118036