Merging Mechanisms in Multilingual Information Retrieval
نویسندگان
چکیده
National Taiwan University (NTU) Natural Language Processing Laboratory (NLPL) participated in MLIR task in CLEF 2002. We submitted five official multilingual runs. In this paper, we try to resolve the collection fusion problem. We experimented with several merging strategies that merge the results of several intermediate runs.
منابع مشابه
Merging Multilingual Information Retrieval Results Based on Prediction of Retrieval Effectiveness
This paper deals with Chinese, English and Japanese multilingual information retrieval (MLIR). Merging problem in distributed MLIR is studied. The prediction of retrieval effectiveness is used to determine the merging weight of each intermediate run. The translation penalty and collection weight are considered to improve merging performance. Several merging strategies are experimented. Experime...
متن کاملTwo Approaches for Multilingual Question Answering: Merging Passages vs. Merging Answers
One major problem in multilingual Question Answering (QA) is the integration of information obtained from different languages into one single ranked list. This paper proposes two different architectures to overcome this problem. The first one performs the information merging at passage level, whereas the second does it at answer level. In both cases, we applied a set of traditional merging stra...
متن کاملDescription of NTU Approach to NTCIR3 Multilingual Information Retrieval
This paper deals with Chinese, English and Japanese multilingual information retrieval. Several merging strategies, including raw-score merging, round-robin merging, normalized-score merging, and normalizedby-top-k merging, were investigated. Experimental results show that centralized approach is better than distributed approach. In distributed approach, normalized-by-top-k with consideration o...
متن کاملNotes on Experiments with Pseudo Relevance Feedback and Data Merging In Cross-Language Retrieval
In the TREC-8 cross-language information retrieval (CLIR) track, we adopted the approach of using machine translation to prepare a source-language query for use in a target-language retrieval task. We empirically evaluated (1) the effect of pseudo relevance feedback on retrieval performance with two feedback vector length control methods in CLIR, and (2) the effect of multilingual data merging ...
متن کاملCLARIT TREC-8 CLIR Experiments
In the TREC-8 cross-language information retrieval (CLIR) track, we adopted the approach of using machine translation to prepare a source-language query for use in a target-language retrieval task. We empirically evaluated (1) the effect of pseudo relevance feedback on retrieval performance with two feedback vector length control methods in CLIR and (2) the effect of multilingual data merging e...
متن کامل