Technical issues of cross-language information retrieval: a review
Information Processing and Management: an International Journal - Special issue: Cross-language information retrieval
A Nonlinear Mapping for Data Structure Analysis
IEEE Transactions on Computers
Exploiting MDS Projections for Cross-language IR
Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval
Semantic Mapping for Related Term Identification
CICLing '09 Proceedings of the 10th International Conference on Computational Linguistics and Intelligent Text Processing
| Hi-index | 0.00 |
A non-linear semantic mapping procedure is implemented for crosslanguage text matching at the sentence level. The method relies on a non-linear space reduction technique which is used for constructing semantic embeddings of multilingual sentence collections. In the proposed method, an independent embedding is constructed for each language in the multilingual collection and the similarities among the resulting semantic representations are used for cross-language matching. It is shown that the proposed method outperforms other conventional cross-language information retrieval methods.