1 / 15

Foreign Name Backward Transliteration in Chinese-English Cross-Language Image Retrieval

Foreign Name Backward Transliteration in Chinese-English Cross-Language Image Retrieval. Advisor : Dr. Hsu Presenter : Chien Shing Chen Author: Wei-Hao Lin and Hsin-His Chen. Proceedings of 2003 Workshop of Cross Language Evaluation Forum, Norway, August, 2003. Outline. Motivation

noel
Download Presentation

Foreign Name Backward Transliteration in Chinese-English Cross-Language Image Retrieval

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Foreign Name Backward Transliteration in Chinese-English Cross-Language Image Retrieval Advisor :Dr. Hsu Presenter: Chien Shing Chen Author: Wei-Hao Lin and Hsin-His Chen Proceedings of 2003 Workshop of Cross Language Evaluation Forum,Norway, August, 2003.

  2. Outline • Motivation • Objective • Introduction • Backward Transliteration • Query Translation • Experimental Result • Conclusions • Personal Opinion

  3. Motivation • How to retrieve multimedia data precisely a important research issue. • People with no strong language skills can easily understand the relevance of the retrieved images. • IR systems must handle proper nouns transliteration approximately to achieve better performance.

  4. Objective • adopt text-based approach to deal with the Chinese-English cross-language image retrieval problem

  5. Introduction Input MI 1 Chinese English F-2-H-F 2 IPA IPA Similarity score +MI Phoneme Phoneme 3 Similarity score +F2HF 4 F-2-H-F: First –two-highest-frequency MI: Mutual Information

  6. Similarity Measurement-Dynamic • Dynamic programming to trade off : • alignment • similarity scoring matrix M • OPTIMAL • S1 (j h u g oU) • S2 (v k uo)

  7. Candidate Filter • A transliterated word and its original word contain the same phonemes, and the order of the phonemes are the same. • After retrieving, the top rank of candidate words as the appropriate candidates of the transliterated word.

  8. Candidate Filter • x: Chinese phoneme • y: English phoneme

  9. Query Translation • We adopted the following two methods to select appropriate translations: • CO model • adopt MI to measure the co-occurrence strength between words • First-two-highest-frequency • highest occurrence frequency in the English image captions were considered as the target language query terms

  10. Query Translation • 150 distinct Chinese query terms • Total 16 of 150 query terms is unknown word. • The terms contain 7 person names and 5 location names, and were translated by foreign names.

  11. Experiments

  12. Experiments

  13. Experiments

  14. Conclusions • Text-based image retrieval and query translation were adopted in the experiments.

  15. Personal Opinion • Drawback • The corpus is not clear. • Application • apply to text-based IR • Future Work • identify unknown word is still a challenge

More Related