skip to main content
article

Cross-language spoken document retrieval using HMM-based retrieval model with multi-scale fusion

Published:01 March 2003Publication History
Skip Abstract Section

Abstract

Cross-language spoken document retrieval (CL-SDR) is the technology that facilitates automatic retrieval of relevant information from a collection of spoken documents in a language that is different from that used in the queries. Information sources that are in different languages can then be retrieved automatically with CL-SDR, and the number of searchable information sources will increase significantly. The HMM-based retrieval model is a probabilistic formulation for the retrieval problem. Extensions to this retrieval model can be made by taking advantage of its probabilistic nature. Specifically, we have incorporated the translation component to make it possible to perform cross-language information retrieval (CLIR). In addition, this HMM-based CLIR retrieval model is also extended for retrieval at subword scales.In this work the extended HMM-based retrieval model has been applied to an English-Mandarin CL-SDR task, which is to search the Mandarin spoken document collection with English queries at word and subword scales. Retrieval results obtained from these indexing scales are then fused for multi-scale CL-SDR. Experimental results demonstrate that improvement in CL-SDR retrieval performance can be achieved by fusion of word and subword scales.

References

  1. BAI, B. R., CHEN, B., AND WANG, H. M. 2000. Syllable-based Chinese text/spoken document retrieval using text/speech queries. J. Pattern Recogn. Artif. Intell. 4, 603--616.Google ScholarGoogle Scholar
  2. BALLESTEROS, L. AND CROFT, W. B. 1997. Phrasal translation and query expansion techniques for cross-language information retireval. In Proceedings of the 20th ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, 84--91. Google ScholarGoogle Scholar
  3. BARTELL, B. T., COTTRELL, G. W., AND BELEW, R. K. 1994. Automatic combination of multiple ranked retrieval systems. In Proceedings of the 17th ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, 173--181. Google ScholarGoogle Scholar
  4. BBN. 2000. Identifinder(TM). http://www.bbn.com/speech/identifinder.html.Google ScholarGoogle Scholar
  5. BELKIN, N. J., KANTOR, P., FOX, E. A., AND SHAW, J. A. 1995. Combining the evidence of multiple query representations for information retrieval. Inf. Process. Manage. 31, 431--448. Google ScholarGoogle Scholar
  6. BERGER, A. AND LAFFERTY, J. 1999a. Information retrieval as statistical translation. In Proceedings of the 22nd ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, 222--229. Google ScholarGoogle Scholar
  7. BERGER, A. AND LAFFERTY, J. 1999b. The Weaver system for document retrieval. In Proceedings of the 8th Text REtrieval Conference. NIST, 163--174.Google ScholarGoogle Scholar
  8. BRASCHLER, M., KRAUSE, J., PETERS, C., AND SCHAUBLE, P. 1998. Cross-language information retrieval (CLIR) track overview. In Proceedings of the 7th Text REtrieval Conference. NIST.Google ScholarGoogle Scholar
  9. CHEN, A. 2000. Phrasal translation for English-Chinese cross language information retrieval. In Proceedings of Workshop on English-Chinese Cross Language Information Retrieval at the 2000 International Conference on Chinese Language Computing. 195--202.Google ScholarGoogle Scholar
  10. CHEN, A. 2001. Berkeley at NTCIR-2: Chinese, Japanese, and English IR experiments. In Proceedings of the 2nd NTCIR Workshop Meeting on Evaluation of Chinese and Japanese Text Retrieval and Text Summarization. 32--39.Google ScholarGoogle Scholar
  11. CHEN, A., JIANG, H., AND GEY, F. 2000. English-Chinese cross-language IR using bilingual dictionaries. In Proceedings of the 9th Text REtrieval Conference. NIST.Google ScholarGoogle Scholar
  12. CHEN, B., WANG, H. M., AND LEE, L. S. 2000. Retrieval of broadcast news speech in Mandarin Chinese collected in Taiwan using syllable-level statistical characteristics. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing. 1771--1774.Google ScholarGoogle Scholar
  13. CHEN, B., WANG, H. M., ANDLEE, L. S. 2001. An HMM/N-gram-based linguistic processing approach for Mandarin spoken document retrieval. In Proceedings of the 7th European Conference on Speech Communication and Technology. Vol. 2. 1045--1048.Google ScholarGoogle Scholar
  14. FOX, E. A. AND SHAW, J. 1993. Combination of multiple searches. In Proceedings of the 2nd Text REtrieval Conference. NIST, 243--252.Google ScholarGoogle Scholar
  15. GAO, J., NIE, J. Y., XUN, E., ZHANG, J., ZHOU, M., AND HUANG, C. 2001. Improving query translation for cross-language information retrieval using statistical models. In Proceedings of the 24th ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, 96--104. Google ScholarGoogle Scholar
  16. GAO, J., NIE, J. Y., ZHANG, J., AND XUN, E. 2000. TREC-9 CLIR experiments at MSRCN. In Proceedings of the 9th Text REtrieval Conference. NIST, 343--353.Google ScholarGoogle Scholar
  17. GAROFOLO, J. S., AUZANNE, C. G. P., AND VOORHEES, E. M. 1999. The TREC spoken document retrieval track: A success story. In Proceedings of the 8th Text REtrieval Conference. NIST, 107--129.Google ScholarGoogle Scholar
  18. GAROFOLO, J. S., VOORHEES, E. M., AUZANNE, C. G. P., STANFORD, V. M., AND LUND, B. A. 1998. 1998 TREC-7 spoken document retrieval track overview and results. In Proceedings of the 7th Text REtrieval Conference. NIST, 79--89.Google ScholarGoogle Scholar
  19. GAROFOLO, J. S., VOORHEES, E. M., STANFORD, V. M., AND JONES, K. S. 1997. TREC-6 1997 spoken document retrieval track overview and results. In Proceedings of the 6th Text REtrieval Conference. NIST, 83--91.Google ScholarGoogle Scholar
  20. GREFENSTETTE, G. 1998. Cross-Language Information Retrieval. Kluwer Academic, Boston MA. Google ScholarGoogle Scholar
  21. HAUPTMANN, A. G., SCHEYTT, P., WACTLAR, H. D., AND KENNEDY, P. E. 1998. Multi-lingual Informedia: A demonstration of speech recognition and information retrieval across multiple languages. In Proceedings of 1998 Broadcast News Transcription and Understanding Workshop.Google ScholarGoogle Scholar
  22. HIEMSTRA, D. 2000. Using language models for information retrieval. Ph.D. thesis, Centre for Telematics and Information Technology, University of Twente,.Google ScholarGoogle Scholar
  23. HUANG, S., BIAN, X., WU, G., AND MCLEMORE, C. 1997. CALLHOME Mandarin Chinese lexicon. Tech. Rep., Linguistic Data Consortium, {online} http://www.ldc.upenn.edu/Catalog/LDC96L15.html.Google ScholarGoogle Scholar
  24. HULL, D. A. AND GREFENSTETTE, G. 1996. Querying across languages: A dictionary-based approach to multilingual information retrieval. In Proceedings of the 19th ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, 49--57. Google ScholarGoogle Scholar
  25. KWOK, K. L. 1997. Comparing representations in Chinese information retrieval. In Proceedings of the 20th ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, 34--41. Google ScholarGoogle Scholar
  26. KWOK, K. L. 1999. English-Chinese cross-language retrieval based on a translation package. In Proceedings of the Workshop of Machine Translation for Cross Language Information Retrieval, Machines Translation Summit VII.Google ScholarGoogle Scholar
  27. LDC. 2000. Project topic detection and tracking phase two (TDT-2). Linguistic Data Consortium. http://www.ldc.upenn.edu/Projects/TDT2.Google ScholarGoogle Scholar
  28. LEVOW, G. A. AND OARD, D. W. 2000. Translingual topic tracking: Applying lessons from the MEI project. In Proceedings of the 2000 Topic Detection and Tracking Workshop.Google ScholarGoogle Scholar
  29. LO, W. K., SCHONE, P., AND MENG, H. M. 2001. Multi-scale retrieval in MEI: an English-Chinese translingual speech retrieval system. In Proceedings of the 7th European Conference on Speech Communication and Technology. Vol. 2. 1303--1306.Google ScholarGoogle Scholar
  30. MAKHOUL, J., KUBALA, F., LEEK, T., LIU, D., NGUYEN, L., SCHWARTZ, R., AND SRIVASTAVA, A. 2000. Speech and language technologies for audio indexing and retrieval. Proc. IEEE 88, 1338--1353.Google ScholarGoogle Scholar
  31. MATEEV, B., MUNTEANU, E., SHERIDAN, P., WECHSLER, M., AND SCHAUBLE, P. 1997. ETH TREC-6: Routing, Chinese, cross-language and spoken document retrieval. In Proceedings of the 6th Text REtrieval Conference. NIST, 623--636.Google ScholarGoogle Scholar
  32. MENG, H. M., CHEN, B., GRAMS, E., KHUDANPUR, S., LO, W. K., LEVOW, G. A., OARD, D., SCHONE, P., TANG, K., WANG, H. M., AND WANG, J. Q. 2000. Mandarin-English information (MEI): Investigating translingual speech retrieval. Tech. Rep., Johns Hopkins Univ., Baltimore, MD. Final report: {online} http//www.clsp.jhu.edu/ws2000/final_reports/mei.Google ScholarGoogle Scholar
  33. MENG, H. M., CHEN, B., KHUDANPUR, S., LEVOW, G. A., LO, W. K., OARD, D., SCHONE, P., TANG, K., WANG, H. M., AND WANG, J. Q. 2001. Mandarin-English information (MEI): Investigating translingual speech retrieval. In Proceedings of the 2001 Human Language Technology Conference. Google ScholarGoogle Scholar
  34. MENG, H. M., LO, W. K., LI, Y. C., AND CHING, P. C. 2000. Multi-scale audio indexing for Chinese spoken document retrieval. In Proceedings of the 6th International Conference on Spoken Language Processing. Vol. IV. 101--104.Google ScholarGoogle Scholar
  35. MILLER, D. R. H., LEEK, T., AND SCHWARTZ, R. M. 1998. BBN at TREC7: Using hidden Markov models for information retrieval. In Proceedings of the 7th Text REtrieval Conference. NIST, 133--142.Google ScholarGoogle Scholar
  36. NG, K. 2000. Subword-based approaches for spoken document retrieval. Speech Commun. 32, 157--186. Google ScholarGoogle Scholar
  37. NIE, J. Y. AND REN, F. 1999. Chinese information retrieval: using characters or words? Inf. Process. Manage. 35, 443--462.Google ScholarGoogle Scholar
  38. NIE, J. Y., SIMARD, M., ISABELLE, P., AND DURAND, R. 1999. Cross-language information retrieval based on parallel texts and automatic mining of parallel texts. In Proceedings of the 22th ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, 74--81. Google ScholarGoogle Scholar
  39. PIRKOLA, A., HEDLUND, T., AND KESKUSTALO, H. 2001. Dictionary-based cross-language information retrieval: problems, methods and research findings. Inf. Retrieval 4, 209--230. Google ScholarGoogle Scholar
  40. RESNIK, P., OARD, D. W., AND LEVOW, G. A. 2001. Improved cross-language retrieval using backoff translation. In Proceedings of the 2001 Human Language Technology Conference. Google ScholarGoogle Scholar
  41. SALTON, G. AND MCGILL, M. 1983. Introduction to Modern Information Retrieval. McGraw-Hill, New York. Google ScholarGoogle Scholar
  42. SCHAUBLE, P. AND SHERIDAN, P. 1997. Cross-language information retrieval (CLIR) track overview. In Proceedings of the 6th Text REtrieval Conference. NIST, 31--44.Google ScholarGoogle Scholar
  43. SHERIDAN, P. AND BALLERINI, J. P. 1996. Experiments in multilingual information retrieval using the SPIDER system. In Proceedings of the 19th ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, 58--65. Google ScholarGoogle Scholar
  44. SHERIDAN, P., BRASCHLER, M., AND SCHAUBLE, P. 1997. Cross-language information retrieval in a multi-lingual legal domain. In Proceedings of the 1st European Conference on Research and Advanced Technology for Digital Libraries. 253--268. Google ScholarGoogle Scholar
  45. SHERIDAN, P., WECHSLER, M., AND SCHAUBLE, P. 1997. Cross language speech retrieval: Establishing a baseline performance. In Proceedings of the 20th ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, 99--108. Google ScholarGoogle Scholar
  46. SONG, F. AND CROFT, W. B. 1999a. A general language model for information retrieval. In Proceedings of the 8th International Conference on Information and Knowledge Management. 316--321. Google ScholarGoogle Scholar
  47. SONG, F. AND CROFT, W. B. 1999b. A general language model for information retrieval. In Proceedings of the 22th ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, 279--280. Google ScholarGoogle Scholar
  48. VOGT, C. C. AND COTTRELL, G. W. 1999. Fusion via a linear combination of scores. Inf. Retrieval 1, 151--173. Google ScholarGoogle Scholar
  49. WANG, H. M. 2000. Experiments in syllable-based retrieval of broadcast news speech inMandarin Chinese. Speech Commun. 32, 49--60. Google ScholarGoogle Scholar
  50. WANG, H. M. AND CHEN, B. 2001. Comparison of word and subword indexing techniques for Mandarin Chinese spoken document retrieval. In Proceedings of the 2nd Pacific-Rim Conference on Multimedia. Google ScholarGoogle Scholar
  51. WANG, H. M., MENG, H. M., SCHONE, P., CHEN, B., AND LO, W. K. 2001. Multi-scale audio indexing for translingual spoken document retrieval. In Proceedings of International Conference on Acoustics, Speech, and Signal Processing. Vol. 1. 605--608.Google ScholarGoogle Scholar
  52. WOODLAND, P. C., JOHNSON, S. E., JOURLIN, P., AND JONES, K. S. 2000. Effect of out of vocabulary words in spoken document retrieval. In Proceedings of the 23rd ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, 372--374. Google ScholarGoogle Scholar
  53. XU, J. AND WEISCHEDEL, R. 2000. TREC-9 cross-lingual retrieval at BBN. In Proceedings of the 9th Text REtrieval Conference. NIST, 106--115.Google ScholarGoogle Scholar
  54. ZHAI, C. AND LAFFERTY, J. 2001. A study of smoothing methods for language models applied to ad hoc information retrieval. In Proceedings of the 24th ACM SIGIR Conference on Research and Development in Information Retrieval. ACM Press, New York, 334--342. Google ScholarGoogle Scholar
  55. ZHAN, P. 1999. Dragon systems' 1998 broadcast news transcription system for Mandarin. In Proceedings of the DARPA Broadcast News Workshop '99.Google ScholarGoogle Scholar

Index Terms

  1. Cross-language spoken document retrieval using HMM-based retrieval model with multi-scale fusion

    Recommendations

    Comments

    Login options

    Check if you have access through your login credentials or your institution to get full access on this article.

    Sign in

    Full Access

    PDF Format

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader