Abstract | ||
---|---|---|
This document describes the preliminary release of the integrated Kyoto system for specific domain WSD. The system uses concept miners (Tybots) to extract domain-related terms and produces a domain-related thesaurus, followed by knowledge-based WSD based on wordnet graphs (UKB). The resulting system can be applied to any language with a lexical knowledge base, and is based on publicly available software and resources. Our participation in Semeval task #17 focused on producing running systems for all languages in the task, and we attained good results in all except Chinese. Due to the pressure of the time-constraints in the competition, the system is still under development, and we expect results to improve in the near future. |
Year | Venue | Keywords |
---|---|---|
2010 | SemEval@ACL | semeval task,resulting system,specific domain,lexical knowledge base,integrated system,concept miner,knowledge-based wsd,domain-related thesaurus,integrated kyoto system,available software,domain-related term,good result |
Field | DocType | Citations |
Graph,SemEval,Computer science,Lexical knowledge,Software,Artificial intelligence,Natural language processing,WordNet | Conference | 2 |
PageRank | References | Authors |
0.36 | 8 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aitor Soroa | 1 | 1121 | 59.72 |
Eneko Agirre | 2 | 3119 | 217.33 |
Oier Lopez De Lacalle | 3 | 382 | 25.08 |
Monica Monachini | 4 | 2 | 0.36 |
Jessie Lo | 5 | 2 | 0.36 |
Shu-kai Hsieh | 6 | 47 | 21.47 |
Wauter Bosma | 7 | 97 | 10.83 |
Piek Vossen | 8 | 387 | 61.59 |