Name
Abstract | ||
|---|---|---|
Many ways of dealing with large collections of linguistic information involve the general principle of mapping words, larger terms and documents into some sort of abstract space. Considerable effort has been devoted to applying such techniques for practical tasks such as information retrieval and word-sense disambiguation. However, the inherent structure of these spaces is often less well-understood.Visualisation tools can help to uncover the relationships between meanings in this space, giving a clearer picture of the natural structure of linguistic information. We present a variety of tools for visualising word-meanings in vector spaces and graph models, derived from co-occurrence information and local syntactic analysis. Our techniques suggest new solutions to standard problems such as automatic management of lexical resources, which perform well under evaluation.The tools presented in this paper are all available for public use on our website. |
Year | DOI | Venue |
|---|---|---|
2002 | 10.1007/3-540-46154-X_14 | TSD |
Keywords | Field | DocType |
co-occurrence information,abstract space,analysing meaning,information retrieval,natural structure,vector space,considerable effort,automatic management,visualisation techniques,inherent structure,clearer picture,linguistic information | Information structure,Rule-based machine translation,Semantic similarity,Cosine similarity,Computer science,sort,Natural language processing,Artificial intelligence,Parsing,Latent semantic analysis,Abstract space | Conference |
ISBN | Citations | PageRank |
3-540-44129-8 | 14 | 1.50 |
References | Authors | |
7 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dominic Widdows | 1 | 640 | 47.45 |
| Scott Cederberg | 2 | 34 | 4.14 |
| Beate Dorow | 3 | 186 | 11.94 |