On the Evaluation of Entity Profiles
Autor: | de Rijke, M., Balog, K., Bogers, A.M., van den Bosch, A., Agosti, M., Ferro, N., Peters, C., Smeaton, A. |
---|---|
Přispěvatelé: | Information and Language Processing Syst (IVI, FNWI), Creative Computing |
Rok vydání: | 2010 |
Předmět: |
evaluation
Information retrieval Computer science 02 engineering and technology entity search 16. Peace & justice entity profiling entity retrieval Semantic similarity 020204 information systems 0202 electrical engineering electronic engineering information engineering Ontology Profiling (information science) 020201 artificial intelligence & image processing Precision and recall |
Zdroj: | Multilingual and Multimodal Information Access Evaluation ISBN: 9783642159978 CLEF Multilingual and Multimodal Information Access Evaluation: international conference of the Cross-Language Evaluation Forum, CLEF 2010, Padua, Italy, September 20-23, 2010 : proceedings, 94-99 STARTPAGE=94;ENDPAGE=99;TITLE=Multilingual and Multimodal Information Access Evaluation de Rijke, M, Balog, K, Bogers, T & van den Bosch, A 2010, ' On the Evaluation of Entity Profiles ', Paper presented at Conference on Multilingual and Multimodal Information Access Evaluation (CLEF 2010), Padua, Italy, 20/09/2010-23/09/2010 . CLEF2010: Conference on Multilingual and Multimodal Information Access Evaluation, 94-99 STARTPAGE=94;ENDPAGE=99;TITLE=CLEF2010 |
DOI: | 10.1007/978-3-642-15998-5_11 |
Popis: | Entity profiling is the task of identifying and ranking descriptions of a given entity. The task may be viewed as one where the descriptions being sought are terms that need to be selected from a knowledge source (such as an ontology or thesaurus). In this case, entity profiling systems can be assessed by means of precision and recall values of the descriptive terms produced. However, recent evidence suggests that more sophisticated metrics are needed that go beyond mere lexical matching of system-produced descriptors against a ground truth, allowing for graded relevance and rewarding diversity in the list of descriptors returned. In this note, we motivate and propose such a metric. |
Databáze: | OpenAIRE |
Externí odkaz: |