Causal Reconstruction
Causal reconstruction is the task of reading a written causal description of a physical behavior, forming an internal model of the described activity, and demonstrating comprehension through question answering. T his task is difficult because written d escriptions often do not specify exactly ho...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/5955 |
| _version_ | 1811097043355041792 |
|---|---|
| author | Borchardt, Gary C. |
| author_facet | Borchardt, Gary C. |
| author_sort | Borchardt, Gary C. |
| collection | MIT |
| description | Causal reconstruction is the task of reading a written causal description of a physical behavior, forming an internal model of the described activity, and demonstrating comprehension through question answering. T his task is difficult because written d escriptions often do not specify exactly how r eferenced events fit together. This article (1) ch aracterizes the causal reconstruction problem, (2) presents a representation called transition space, which portrays events in terms of "transitions,'' or collections of changes expressible in everyday language, and (3) describes a program called PATHFINDER, which uses the transition space representation to perform causal reconstruction on simplified English descriptions of physical activity. |
| first_indexed | 2024-09-23T16:53:25Z |
| id | mit-1721.1/5955 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:53:25Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/59552019-04-10T17:24:24Z Causal Reconstruction Borchardt, Gary C. knowledge representation explanation causal reasoning sanalogy abstraction natural language Causal reconstruction is the task of reading a written causal description of a physical behavior, forming an internal model of the described activity, and demonstrating comprehension through question answering. T his task is difficult because written d escriptions often do not specify exactly how r eferenced events fit together. This article (1) ch aracterizes the causal reconstruction problem, (2) presents a representation called transition space, which portrays events in terms of "transitions,'' or collections of changes expressible in everyday language, and (3) describes a program called PATHFINDER, which uses the transition space representation to perform causal reconstruction on simplified English descriptions of physical activity. 2004-10-04T14:16:02Z 2004-10-04T14:16:02Z 1993-02-01 AIM-1403 http://hdl.handle.net/1721.1/5955 en_US AIM-1403 61 p. 548466 bytes 2780985 bytes application/octet-stream application/pdf application/octet-stream application/pdf |
| spellingShingle | knowledge representation explanation causal reasoning sanalogy abstraction natural language Borchardt, Gary C. Causal Reconstruction |
| title | Causal Reconstruction |
| title_full | Causal Reconstruction |
| title_fullStr | Causal Reconstruction |
| title_full_unstemmed | Causal Reconstruction |
| title_short | Causal Reconstruction |
| title_sort | causal reconstruction |
| topic | knowledge representation explanation causal reasoning sanalogy abstraction natural language |
| url | http://hdl.handle.net/1721.1/5955 |
| work_keys_str_mv | AT borchardtgaryc causalreconstruction |