Summary of the paper
| Title | Automatic Discovery of Semantic Relations using MindNet |
|---|---|
| Authors | Zareen Syed, Evelyne Viegas and Savas Parastatidis |
| Abstract | Information extraction deals with extracting entities (such as people,organizations or locations) and named relations between entities (such as"People born-in Country") from text documents. An important challenge ininformation extraction is the labeling of training data which is usually donemanually and is therefore very laborious and in certain cases impractical. Thispaper introduces a new “model” to extract semantic relations fullyautomatically from text using the Encarta encyclopedia and lexical-semanticrelations discovered by MindNet. MindNet is a lexical knowledge base that canbe constructed fully automatically from a given text corpus without any humanintervention. Encarta articles are categorized and linked to related articlesby experts. We demonstrate how the structured data available in Encarta and thelexical semantic relations between words in MindNet can be used to enrichMindNet with semantic relations between entities. With a slight trade off ofaccuracy a semantically enriched MindNet can be used to extract relations froma text corpus without any human intervention. |
| Language | Other |
| Topics | Information Extraction, Information Retrieval, Semantics, Other |
Full paper  |
Automatic Discovery of Semantic Relations using MindNet |
| Bibtex | @InProceedings{SYED10.78, author = {Zareen Syed, Evelyne Viegas and Savas Parastatidis}, title = {Automatic Discovery of Semantic Relations using MindNet}, 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} } |