Taking advantage of top-ranked documents in response to a query for improving quality of query translation has been shown to be an effective approach for cross-language information retrieval. In this paper, we propose a new method for query translation based on dimension projection of embedded vectors from the pseudo-relevant documents in the source language to their equivalents in the target language. To this end, first we learn low-dimensional representations of the words in the pseudo-relevant collections separately and then aim at finding a query-dependent transformation matrix between the vectors of translation pairs. At the next step, representation of each query term is projected to the target language and then, after using a softmax function, a query-dependent translation model is built. Finally, the model is used for query translation. Our experiments on four CLEF collections in French, Spanish, German, and Persian demonstrate that the proposed method outperforms all competitive baselines in language modelling, particularly when it is combined with a collection-dependent translation model.
from cs.AI updates on arXiv.org http://ift.tt/1TFe8Kp
via IFTTT
No comments:
Post a Comment