Abstract
We present a learning device able to deduce a set of Danish color and shape terms. Only two data sources are available to the learner: A phonetic transcription of a human informant solving a description task, and a minimal formal model of the picture being described. The system thus contains no preconceived lexical, morphological, or semantic categories. The test data are from the phonetic corpus DanPASS, a standard Danish reference corpus. The learning device, called InShape-2, is an early result of an ambitious research programme at CMOL on data-driven language learning.
| Original language | English |
|---|---|
| Journal | NEALT (Northern European Association of Language Technology) Proceedings Series |
| Issue number | 11 |
| Pages (from-to) | 90-97 |
| Number of pages | 8 |
| ISSN | 1736-6305 |
| Publication status | Published - 2011 |
| Event | NODALIDA 2011. The 18th Nordic Conference of Computational Linguistics - Riga, Latvia Duration: 11 May 2011 → 13 May 2011 Conference number: 18 http://www.lumii.lv/nodalida2011/ |
Conference
| Conference | NODALIDA 2011. The 18th Nordic Conference of Computational Linguistics |
|---|---|
| Number | 18 |
| Country/Territory | Latvia |
| City | Riga |
| Period | 11/05/2011 → 13/05/2011 |
| Internet address |