Context-Sensitive Measurement of Word Distance by Adaptive Scaling of a Semantic Space
| dc.creator | Kozima, Hideki | |
| dc.creator | Ito, Akira | |
| dc.date | 1996-01-23 | |
| dc.date | 1996-06-25 | |
| dc.date.accessioned | 2026-07-07T09:02:19Z | |
| dc.date.available | 2026-07-07T09:02:19Z | |
| dc.description | The paper proposes a computationally feasible method for measuring context-sensitive semantic distance between words. The distance is computed by adaptive scaling of a semantic space. In the semantic space, each word in the vocabulary V is represented by a multi-dimensional vector which is obtained from an English dictionary through a principal component analysis. Given a word set C which specifies a context for measuring word distance, each dimension of the semantic space is scaled up or down according to the distribution of C in the semantic space. In the space thus transformed, distance between words in V becomes dependent on the context C. An evaluation through a word prediction task shows that the proposed measurement successfully extracts the context of a text. | |
| dc.description | 8 pages, single LaTeX file | |
| dc.identifier | https://arxiv.org/abs/cmp-lg/9601007 | |
| dc.identifier | http://arxiv.org/abs/cmp-lg/9601007 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/148589 | |
| dc.subject | Computation and Language | |
| dc.title | Context-Sensitive Measurement of Word Distance by Adaptive Scaling of a Semantic Space | |
| dc.type | text |