NTCIR-3 WEB Experiments at Osaka Kyoiku University - Towards Index Partitioning and Parallel Retrieval
نویسندگان
چکیده
Long gram-based indices are experimented at NTCIR-3 WEB task. To make gram-based indices, no analyses such as morphological ones are required. 2 byte characters extracted from NTCIR-3 ‘cooked’ version of WEB task corpus. The total index size is 26 Gbyte and time to make indices is about 18 hours. Median search time per word from index is 197msec. Ranking algorithm used is based on a traditional probabilistic model. We report index partitioning which we experimented. And we propose parallel retrieval.
منابع مشابه
NTCIR-4 WEB Experiments at Osaka Kyoiku University - Static/Dynamic Scoring Using Link Structure Analysis and Web Page Grouping
We did gram-based indexing and the retrieval with NTCIR-4 WEB task. The time required to make indices are 34.7 hours. The size of indices is 30.2Gbyte. The median of retrieval time par word is 26msec. The ranking algorithm of retrieval results is based on a traditional probabilistic model. We report on the result of gram-based indexing and the retrieval, and propose a scoring method based on li...
متن کاملNTCIR-6 CLIR Experiments at Osaka Kyoiku University - Term Expansion Using Online Dictionaries and Weighting Score by Term Variety
This paper describes experimental results of J-J subtask of NTCIR-6 CLIR. We expanded query term using online dictionaries in a WEB. It was effective for some topics of which average precision was low. Probabilistic model were employed for scoring, and we modified this score multiplying by the number of varieties of query terms, also. In most cases this works well. Query term reduction should b...
متن کاملNTCIR-3 CLIR Experiments at Osaka Kyoiku University - Comparison of Gram-based Indices
Long gram-based indices are experimented at NTCIR-3 CLIR task. To make gram-based indices, no analyses such as morphological ones are required. Indices in three languages (i.e. Japanese, English and Chinese) are made at this task. They are quite different in some point. The difference of index overhead comes from the difference of character code for example.
متن کاملNTCIR-3 PAT Experiments at Osaka Kyoiku University: Long Gram-based Index and Essential Words
Long gram-based indices are experimented at NTCIR-3 patent task. To make gram-based indices, no analyses such as morphological ones are required. The docno, abj, clj and dej tag fields are extracted from NTCIR-3 patent corpus. The total index size is 11.4Gbyte and time to make indices is about 8.7 hours. Median search time per word from abj and dej index is 9.8msec and 91.8msec respectively. Av...
متن کاملNTCIR-4 PATENT Experiments at Osaka Kyoiku University - Gram-Based Passage Index and Essential Words
Long gram-based indices are experimented at NTCIR-4 patent task. No morphological analyses are required to make gram-based indices. The ABJ and DEJ tag fields are extracted and indexed from NTCIR-4 patent corpus. Passages are extracted and indexed also. The total index size is 240Gbyte and time to make indices is about 86 hours. By merging the result of passage retrieval with the result of docu...
متن کامل