Abstract
Language exhibits combinatorial productivity as complex constructions are composed of simple elements in a linear or hierarchical fashion. Complexity arises as one cannot be exposed to all possible combinations during ontogeny and yet to master a language one need to be, and very often is, able to generalise to process and comprehend constructions that are of novel combinations. Accounting for such an ability is a current challenge being tackled in connectionist research. In this study, we will first demonstrate that connectionist networks do generalise towards combinatorial productivity followed by an investigation of how the networks could achieve that.
| Original language | English |
|---|---|
| Title of host publication | 2007 INTERNATIONAL CONFERENCE ON INTEGRATION OF KNOWLEDGE INTENSIVE MULTI-AGENT SYSTEMS |
| Publisher | IEEE |
| Pages | 139-+ |
| Number of pages | 3 |
| ISBN (Print) | 978-1-4244-0944-0 |
| Publication status | Published - 2007 |
| Event | International Conference on Integration of Knowledge Intensive Multi-Agent Systems - Waltham, Morocco Duration: 30 Apr 2007 → 3 May 2007 |
Conference
| Conference | International Conference on Integration of Knowledge Intensive Multi-Agent Systems |
|---|---|
| Country/Territory | Morocco |
| City | Waltham |
| Period | 30/04/07 → 3/05/07 |
Funding
The authors would like to thank James MTNETT, Tao GONG, Susan SHUAI, and Hongying ZHENG for comments and discussions. The research is supported by research grants from the RGC Hong Kong: CUHK-1224/02H and CUHK-1127/04H.
Research Keywords
- SYNTACTIC CATEGORIES
- INFANTS
- RULES
- TIME
- FORM