Naive Physics, Event Perception, Lexical Semantics, and Language Acquisition
This thesis proposes a computational model of how children may come to learn the meanings of words in their native language. The proposed model is divided into two separate components. One component produces semantic descriptions of visually observed events while the other correlates those de...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6784 |
| _version_ | 1811093754689355776 |
|---|---|
| author | Siskind, Jeffrey M. |
| author_facet | Siskind, Jeffrey M. |
| author_sort | Siskind, Jeffrey M. |
| collection | MIT |
| description | This thesis proposes a computational model of how children may come to learn the meanings of words in their native language. The proposed model is divided into two separate components. One component produces semantic descriptions of visually observed events while the other correlates those descriptions with co-occurring descriptions of those events in natural language. The first part of this thesis describes three implementations of the correlation process whereby representations of the meanings of whole utterances can be decomposed into fragments assigned as representations of the meanings of individual words. The second part of this thesis describes an implemented computer program that recognizes the occurrence of simple spatial motion events in simulated video input. |
| first_indexed | 2024-09-23T15:50:08Z |
| id | mit-1721.1/6784 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:50:08Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/67842019-04-11T02:53:07Z Naive Physics, Event Perception, Lexical Semantics, and Language Acquisition Siskind, Jeffrey M. This thesis proposes a computational model of how children may come to learn the meanings of words in their native language. The proposed model is divided into two separate components. One component produces semantic descriptions of visually observed events while the other correlates those descriptions with co-occurring descriptions of those events in natural language. The first part of this thesis describes three implementations of the correlation process whereby representations of the meanings of whole utterances can be decomposed into fragments assigned as representations of the meanings of individual words. The second part of this thesis describes an implemented computer program that recognizes the occurrence of simple spatial motion events in simulated video input. 2004-10-20T19:54:56Z 2004-10-20T19:54:56Z 1993-04-01 AITR-1456 http://hdl.handle.net/1721.1/6784 en_US AITR-1456 285 p. 697015 bytes 3782562 bytes application/octet-stream application/pdf application/octet-stream application/pdf |
| spellingShingle | Siskind, Jeffrey M. Naive Physics, Event Perception, Lexical Semantics, and Language Acquisition |
| title | Naive Physics, Event Perception, Lexical Semantics, and Language Acquisition |
| title_full | Naive Physics, Event Perception, Lexical Semantics, and Language Acquisition |
| title_fullStr | Naive Physics, Event Perception, Lexical Semantics, and Language Acquisition |
| title_full_unstemmed | Naive Physics, Event Perception, Lexical Semantics, and Language Acquisition |
| title_short | Naive Physics, Event Perception, Lexical Semantics, and Language Acquisition |
| title_sort | naive physics event perception lexical semantics and language acquisition |
| url | http://hdl.handle.net/1721.1/6784 |
| work_keys_str_mv | AT siskindjeffreym naivephysicseventperceptionlexicalsemanticsandlanguageacquisition |