Research on Cross-Language Retrieval Using Bilingual Word Vectors in Different Languages

• 作者: Dong Zhou Yulong Li
• 来源期刊: 国际计算机前沿大会会议论文集
• 学科: 社会科学
• 关键词: CROSS-LANGUAGE information retrieval BILINGUAL word EMBEDDING Genetic PROXIMITY Language PAIRS
• 年，卷（期）: 2019,（1）
• 页码范围: 462-465
• 页数: 4页
• 分类号: C

摘要

Bilingual word vectors have been exploited a lot in cross-language information retrieval research. However, most of the research is currently focused on similar language pairs. There are very few studies exploring the impact of using bilingual word vectors for cross-language information retrieval in long-distance language pairs. In this paper, it systematically analyzes the retrieval performance of various European languages (English, German, Italian, French, Finnish, Dutch) as well as Asian languages (Chinese, Japanese) in the adhoc task of CLEF 2002–2003 campaign. Genetic proximity was used to visually represent the relationships between languages and compare their crosslingual retrieval performance in various settings. The results show that the differences in language vocabulary would dramatically affect the retrieval performance. At the same time, the term by term translation retrieval method performs slightly better than the simple vector addition retrieval methods. It proves that the translation-based retrieval model can still maintain its advantage under the new semantic scheme.