作者: Paul Clough
DOI: 10.1007/11519645_60
关键词: Artificial intelligence 、 Query optimization 、 RDF query language 、 Computer science 、 Query language 、 Relevance feedback 、 Web query classification 、 Object Query Language 、 Web search query 、 Query expansion 、 Natural language processing 、 Image retrieval 、 Ranking (information retrieval) 、 Natural language 、 Information access 、 Query by Example 、 Machine translation 、 Data control language
摘要: For many cross-language retrieval tasks, the predominant approach is to translate query into language of document collection (target language). This often gives results as good as, if not better, than translating (source In this paper, we evaluate versus translation for ImageCLEF 2004 bilingual ad hoc task. Image achieved through matching textual queries associated image captions following languages: French, German, Spanish and Italian using commercially publicly available resources. On average, find outperform (77% English MAP compared 65% respectively) but varies widely across query. Combining achieve an average 85% English.