Summary of the paper
| Title | Exploring the Relationship between Semantic Spaces and Semantic Relations |
|---|---|
| Authors | Akira Utsumi |
| Abstract | This study examines the relationship between two kinds of semantic spaces ―i.e., spaces based on term frequency (tf) and word cooccurrence frequency (co)― and four semantic relations ― i.e., synonymy, coordination,superordination, and collocation ― by comparing, for each semantic relation,the performance of two semantic spaces in predicting word association. Thesimulation experiment demonstrates that the tf-based spaces perform better inpredicting word association based on the syntagmatic relation (i.e.,superordination and collocation), while the co-based semantic spaces are suitedfor predicting word association based on the paradigmatic relation (i.e.,synonymy and coordination). In addition, the co-based space with a largercontext size yields better performance for the syntagmatic relation, while theco-based space with a smaller context size tends to show better performance forthe paradigmatic relation. These results indicate that different semanticspaces can be used depending on what kind of semantic relatedness should becomputed. |
| Language | Cognitive methods |
| Topics | Lexicon, lexical database, Knowledge Discovery/Representation, Cognitive methods |
Full paper  |
Exploring the Relationship between Semantic Spaces and Semantic Relations |
| Bibtex | @InProceedings{UTSUMI10.296, author = {Akira Utsumi}, title = {Exploring the Relationship between Semantic Spaces and Semantic Relations}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |