main.dvi

Size: px

Start display at page:

Download "main.dvi"

ひとおしばもと
9 years ago
Views:

1 CREST [email protected] 1 7% PRIME Multi-lingual Information Retrieval Cross-Language Information Retrieval CLIR 1990 CD-ROM a. b. c. d. b CLIR b 70%

2 CLIR CLIR 2.2 (b) 2 (c) (a) 3 2.4

3 4 Altavista 4 Excite PRIME CLIR [2,3,4,5,7,16,17] NTCIR [1, 6] 1960 [10] Cross-Language Information Retrieval PRIME Patent Retrieval In Multi-lingual Environment [8, 14] [9, 11] PRIME [15] [13] [12] / TREC 1 CLEF NTCIR 3 PRIME 1 3 NTCIR

Multi-lingual Environment 6 2000 7 2001 3 [8, 14] 2001 4 2002 3 [9, 11] PRIME [15] 2002 4 2003 3 [13] [12] / TREC 1 CLEF

4 DB PRIME : PRIME 3.5 collaboration PAT-Transer % PAJ (Patent Abstracts of Japan) CD-ROM ,

3 3.3.1 1 95% PAJ (Patent Abstracts of Japan)

5 U 1 D U = u 1,u 2,...,u n D = d 1,d 2,...,d n P (D U) D (1) P (D U) D address space control block associative learning associative memory associative record compressor research facility correlation function factor correlation hash associative memory 2: arg max D P (D U) = arg max P (U D) P (D) (1) P (U D) P (D) 1 (2) P (U D) P (D) D n P (u i d i ) i=1 n 1 P (d i+1 d i ) i=1 (2) P (d i+1 d i ) 1P (u i d i ) address associative block compressor control correlation facility factor function hash learning memory record research space,,, : EM P (u i d i ) 3 associative 1 correlation 2 (3) P (associative ) = 1/3 (3) P (correlation ) = 2/3 P (u i d i ) 2 EM 23,313 10, d i 95% P (u i d i ) u i 2 3 d i

correlation hash associative memory 2: arg max D P (D U) = arg max P (U D) P (D) (1) P (U D) P (D) 1 (2) P (U D) P (D) D n P (u i d i ) i=1 n 1 P (d i+1 d i ) i=1 (2) P (d i+1 d i )

6 transliteration (si-su-temu) system -sy -s -te -m L/R C/K te-ki-su-to text $ -te - x-t $ 423 1,018 (1) (2) U D u i d i P (D U) D P (D U) P (u i d i ) te ki su to $ t e x t $ : (2) P (D) D P (D)=0 3.4 PRIME PRIME 5 natural language processing information retrieval AND Search 6 7 8

) te ki su to $ t 3 1 2 3 0 e 0 0 0 0 0 x 1 2 1 1 0 t 3 1 2 3 0 $ 0 0 0 0 3 4: (2) P (D)

7 5: PRIME PRIME

8 6: (31) (33) (31) 21 Appl.No

7: [54] [ABSTRACT] 1995 1999 5 32,000 100

9 7: [54] [ABSTRACT] , , information retrieval 4 PRIME PRIME

10 8: [1] Atsushi Fujii and Tetsuya Ishikawa. Cross-language information retrieval at ULIS. In Proceedings of the 1st NTCIR Workshop on Research in Japanese Text Retrieval and Term Recognition, pp , [2] Atsushi Fujii and Tetsuya Ishikawa. Cross-language information retrieval for technical documents. In Proceedings of the Joint ACL SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, pp , [3] Atsushi Fujii and Tetsuya Ishikawa. Cross-language information retrieval using compound word translation. In Proceedings of the 18th International Conference on Computer Processing of Oriental Languages, pp , [4] Atsushi Fujii and Tetsuya Ishikawa. Applying machine translation to two-stage cross-language information retrieval. In Proceedings of the 4th Conference of the Association for Machine Translation in the Americas, pp , [5] Atsushi Fujii and Tetsuya Ishikawa. Cross-language information retrieval based on query keyword translation: An Internet search application. International Journal of Computer Processing of Oriental Languages, Vol. 13, No. 1, pp. 1 13, [6] Atsushi Fujii and Tetsuya Ishikawa. Evaluating multilingual information retrieval and clustering at ULIS. In Proceedings of the 2nd NTCIR Workshop Meeting on Evaluation of Chinese & Japanese Text Retrieval and Text Summarization, 2001.

In Proceedings of the Joint ACL SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, pp. 29 37, 1999. [3] Atsushi Fujii and Tetsuya Ishikawa.

11 9:

12 10: alkenyl-containing polydiorganosiloxane iontrapmassspectrometer indolylalkylpiperazinyl pyridine air bag canister diorganopolysiloxane polymer silicone pressure sensitive adhesive compositions cellulose triacetate photographic cellulose triacetate photographic film base vulcanizable elastomeric compound thermal dye transfer system miniature scan confocal microscope electronic-monetary system peristaltic pump 11:

triacetate photographic cellulose triacetate photographic film base vulcanizable elastomeric compound

13 [7] Atsushi Fujii and Tetsuya Ishikawa. Japanese/English cross-language information retrieval: Exploration of query translation and transliteration. Computers and the Humanities, Vol. 35, No. 4, pp , [8] Masatoshi Fukui, Shigeto Higuchi, Youichi Nakatani, Masao Tanaka, Atsushi Fujii, and Tetsuya Ishikawa. Applying a hybrid query translation method to Japanese/English cross-language patent retrieval. In ACM SIGIR Workshop on Patent Retrieval, [9] Shigeto Higuchi, Masatoshi Fukui, Atsushi Fujii, and Tetsuya Ishikawa. PRIME: A system for multi-lingual patent retrieval. In Proceedings of MT Summit VIII, pp , [10] P.E. Mongar. International co-operation in abstracting services for road engineering. The Information Scientist, Vol. 3, pp , [11],,,.., 2001-NL-145, pp , [12],,.. 9, [13],,,.., 2002-NL- 151, pp , [14],,,.. 7, pp , [15],,,. prime. 8, pp , [16],.., Vol. 41, No. 4, pp , [17],.., Vol. J84-D-II, No. 2, pp , 2001.

Applying a hybrid query translation method to Japanese/English cross-language patent retrieval. In ACM SIGIR Workshop on Patent Retrieval, 2000.

A Japanese Word Dependency Corpus ÆüËÜ¸ì¤ÎÃ±¸ì·¸¤ê¼õ¤±¥³¡¼¥Ñ¥¹

A Japanese Word Dependency Corpus 2015 3 18 Special thanks to NTT CS, 1 /27 Bunsetsu? What is it? ( ) Cf. CoNLL Multilingual Dependency Parsing [Buchholz+ 2006] (, Penn Treebank [Marcus 93]) 2 /27 1. 2.