TY - GEN
T1 - Query translation based on visual information
AU - Zhang, Jiao
AU - Huang, Yonggang
AU - Jiang, Qingzhao
AU - Lu, Wenpeng
AU - Shen, Hualei
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/6/8
Y1 - 2018/6/8
N2 - In the field of cross language information retrieval, how to translate the query into the target language, namely query translation, is a fundamental problem. Because of the ambiguity phenomenon, query translation is always a challenge. Existing researches always rely on mining the text information, such as the contextual relationship or word occurrence. Different from existing research efforts, in this paper, we address the query translation issue by mining the visual information of images, and a new query translation method based on visual information (QTVI) is proposed. QTVI has three steps: image search, image set denoising, and translation candidate selection. In step 1, the query and candidate translation are associated with corresponding image set via image search. Since the resulted image sets from step 1 may be unclean, in step 2, we de-noise the image sets via clustering strategy. Finally, in step 3, the final translation is selected from candidates by constructing multi-class classifier based on cleaned image sets. Empirical experiments show that QTVI outperforms Baidu Translation and Google Translation for the query translation task.
AB - In the field of cross language information retrieval, how to translate the query into the target language, namely query translation, is a fundamental problem. Because of the ambiguity phenomenon, query translation is always a challenge. Existing researches always rely on mining the text information, such as the contextual relationship or word occurrence. Different from existing research efforts, in this paper, we address the query translation issue by mining the visual information of images, and a new query translation method based on visual information (QTVI) is proposed. QTVI has three steps: image search, image set denoising, and translation candidate selection. In step 1, the query and candidate translation are associated with corresponding image set via image search. Since the resulted image sets from step 1 may be unclean, in step 2, we de-noise the image sets via clustering strategy. Finally, in step 3, the final translation is selected from candidates by constructing multi-class classifier based on cleaned image sets. Empirical experiments show that QTVI outperforms Baidu Translation and Google Translation for the query translation task.
KW - Cross language information retrieval
KW - Image retrieval
KW - Query translation
KW - Visual information
UR - http://www.scopus.com/inward/record.url?scp=85049771808&partnerID=8YFLogxK
U2 - 10.1109/ICACI.2018.8377521
DO - 10.1109/ICACI.2018.8377521
M3 - Conference contribution
AN - SCOPUS:85049771808
T3 - Proceedings - 2018 10th International Conference on Advanced Computational Intelligence, ICACI 2018
SP - 563
EP - 567
BT - Proceedings - 2018 10th International Conference on Advanced Computational Intelligence, ICACI 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Conference on Advanced Computational Intelligence, ICACI 2018
Y2 - 29 March 2018 through 31 March 2018
ER -