Search

Some measures such as mean average precision and recall level precision are considered as good system-oriented measures, because they concern both precision and recall that are two important aspects for effectiveness evaluation of information retrieval systems. However, such good system-oriented measures suffer from some shortcomings when partial relevance judgments are used. In this paper, we discuss how to rank retrieval systems in the condition of partial relevance judgments, which is common in major retrieval evaluation events such as TREC conferences and NTCIR workshops. Four system-oriented measures, which are mean average precision, recall level precision, normalized discount cumulative gain, and normalized average precision over all documents, are discussed. Our investigation shows that averaging values over a set of queries may not be the most reliable approach to rank a group of retrieval systems. Some alternatives such as Borda count, Condorcet voting, and the Zero-one normalization method, are investigated. Experimental results are also presented for the evaluation of these methods.

Recent advances in the asymptotic resource costs of pattern matching with compressed suffix arrays are attractive, but a key rival structure, the compressed inverted file, has been dismissed or ignored in papers presenting the new structures. In this paper we examine the resource requirements of compressed suffix array algorithms against compressed inverted file data structures for general pattern matching in genomic and English texts. In both cases, the inverted file indexes q-grams, thus allowing full pattern matching capabilities, rather than simple word based search, making their functionality equivalent to the compressed suffix array structures. When using equivalent memory for the two structures, inverted files are faster at reporting the location of patterns when the number of occurrences of the patterns is high.

Recent advances in the asymptotic resource costs of pattern matching with compressed suffix arrays are attractive, but a key rival structure, the compressed inverted file, has been dismissed or ignored in papers presenting the new structures. In this paper we examine the resource requirements of compressed suffix array algorithms against compressed inverted file data structures for general pattern matching in genomic and English texts. In both cases, the inverted file indexes q-grams, thus allowing full pattern matching capabilities, rather than simple word based search, making their functionality equivalent to the compressed suffix array structures. When using equivalent memory for the two structures, inverted files are faster at reporting the location of patterns when the number of occurrences of the patterns is high.

Some measures such as mean average precision and recall level precision are considered as good system-oriented measures, because they concern both precision and recall that are two important aspects for effectiveness evaluation of information retrieval systems. However, such good system-oriented measures suffer from some shortcomings when partial relevance judgments are used. In this paper, we discuss how to rank retrieval systems in the condition of partial relevance judgments, which is common in major retrieval evaluation events such as TREC conferences and NTCIR workshops. Four system-oriented measures, which are mean average precision, recall level precision, normalized discount cumulative gain, and normalized average precision over all documents, are discussed. Our investigation shows that averaging values over a set of queries may not be the most reliable approach to rank a group of retrieval systems. Some alternatives such as Borda count, Condorcet voting, and the Zero-one normalization method, are investigated. Experimental results are also presented for the evaluation of these methods.