Abstract
One important human reading style is target-oriented, which only focuses on target-related contents. This paper reports the realization of a text scanning mechanism that simulates human target reading process. The reading process is simulated by identifying target reading scope and modeling memory operations such as recall, association and forget. The impressions of words change during reading. Experiments show that: (1) the mechanism is in line with human target reading process, (2) the mechanism can extract the target-related content from text, and (3) the mechanism can measure target-oriented text similarity.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2017 13th International Conference on Semantics, Knowledge and Grids, SKG 2017 |
| Publisher | IEEE |
| Pages | 132-138 |
| Number of pages | 7 |
| Volume | 2018-January |
| ISBN (Electronic) | 9781538625583 |
| DOIs | |
| Publication status | Published - 19 Jan 2018 |
| Event | 13th International Conference on Semantics, Knowledge and Grids, SKG 2017 - Beijing, China Duration: 14 Aug 2017 → 15 Aug 2017 |
Conference
| Conference | 13th International Conference on Semantics, Knowledge and Grids, SKG 2017 |
|---|---|
| Country/Territory | China |
| City | Beijing |
| Period | 14/08/17 → 15/08/17 |
Keywords
- simulation
- target reading
- text scanning