Abstract | ||
---|---|---|
In this paper, we propose to build a temporal ontology, which may contribute to the success of time-related applications. Temporal classifiers are learned from a set of time-sensitive synsets and then applied to the whole WordNet to give rise to TempoWordNet. So, each synset is augmented with its intrinsic temporal value. To evaluate TempoWordNet, we use a semantic vector space representation for sentence temporal classification, which shows that improvements may be achieved with the time-augmented knowledge base against a bag-of-ngrams representation. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1145/2567948.2579042 | WWW (Companion Volume) |
Keywords | Field | DocType |
time-related application,time-augmented knowledge base,sentence temporal classification,whole wordnet,semantic vector space representation,bag-of-ngrams representation,temporal classifier,time-sensitive synsets,intrinsic temporal value,sentence time tagging,temporal ontology | Ontology,Data mining,Vector space,Information retrieval,Computer science,Natural language processing,Artificial intelligence,Knowledge base,WordNet,Sentence,Instrumental and intrinsic value | Conference |
Citations | PageRank | References |
2 | 0.38 | 11 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gaël Dias | 1 | 354 | 41.95 |
Mohammed Hasanuzzaman | 2 | 52 | 13.52 |
Stéphane Ferrari | 3 | 5 | 3.16 |
Yann Mathet | 4 | 20 | 4.43 |