R2D2at NTCIR: Using the Relevance-based Superimposition Model
نویسنده
چکیده
Our information retrieval project submitted fully automatic ad-hoc results. We use only description fields as queries. is the baseline tf idf result, and is the result using the proposed RS model which expands document vectors based on the relevance of documents. This method is expected to show better retrieval effectiveness than conventional methods, such as query expansion. The RS run achieved about 12% improvement of precision over the baseline tf idf run .
منابع مشابه
R2D2 at NTCIR 2 Ad-hoc Task: Relevance-based Superimposition Model for IR
This paper describes our evaluation experiments for NTCIR 2 ad-hoc task. We developed a retrieval system using the Relevance-based Superimposition (RS) model, in which document vectors are modified based on the relevance of the documents. The major focus of this year is on combination of the RS model and query expansion (QE). We submitted fully automatic ad-hoc results brought by different para...
متن کاملR2D2 at NTCIR-4 Web Retrieval Task
We evaluated the Relevance-based Superimposition Model at NTCIR 4 Web task A (survey retrieval) and B (target retrieval). We developed a distributed indexing / searching engine for treating the large amount of documents in a practical processing time. Some improvements of the retrieval precisions were achieved algorithmically.
متن کاملDCU at the NTCIR-11 SpokenQuery&Doc Task
We describe DCU’s participation in the NTCIR-11 SpokenQuery&Document task. We participated in the spokenquery spoken content retrieval (SQ-SCR) subtask by using the slide group segments as basic indexing and retrieval units. Our approach integrates normalised prosodic features into a standard BM25 weighting function to increase weights for terms that are prominent in speech. Text queries and re...
متن کاملNTCIR-5 Query Expansion Experiments using Term Dependence Models
This paper reports the results of our experiments performed for the Query Term Expansion Subtask, a subtask of the WEB Task, at the Fifth NTCIR Workshop, and the results of our further experiments. In this paper we mainly investigated: (i) the effectiveness of query formulation by composing or decomposing compound words and phrases of the Japanese language, which is based on a theoretical frame...
متن کاملRanking Retrieval Systems without Relevance Assessments: Revisited
We re-examine the problem of ranking retrieval systems without relevance assessments in the context of collaborative evaluation forums such as TREC and NTCIR. The problem was first tackled by Soboroff, Nicholas and Cahan in 2001, using data from TRECs 3-8 [16]. Our long-term goal is to semi-automate repeated evaluation of search engines; our short-term goal is to provide NTCIR participants with...
متن کامل