Culturally based story understanding

Culture has a strong influence on how stories are understood. Accordingly, a full account of human intelligence must include an account of cultural influences on story understanding. The research reported takes a step toward accounting for cultural differences computationally by extending the Genesis story understanding system so as to enable Genesis to model Chinese and American differences in human story understanding and question answering. I focused on two murder stories discussed in a classic study by Morris and Peng, identified extensions to Genesis needed to model Chinese and American understanding and question answering biases, and developed rules and concepts not already in the Genesis libraries. I determined that one extension, a question-induced story augmentation capability, was needed to handle questions such as "Did Lu kill Shan because America is individualistic?" Another extension, the introduction of abduction rules, was needed to handle common sense background rules such as "If person X kills person Y, then person X must be insane." I also conceived and implemented computational metrics to measure story coherence. I survey the field of cultural psychology and suggest further steps toward an account of culturally variant cognition.

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

2013

Author dc:creator

• Awad, Hiba

Advisor dc:contributor.advisor

• Patrick H. Winston.

• Electrical Engineering and Computer Science.

Statement dc:rights

• M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about 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/1721.1/85403

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/85403