一、单选题(共15小题,每题2分,共计30分)
二、简答题(共6小题,每题5分,共计30分)
三、计算题(共3小题,每题10分,共计30分)
四、案例题(共3小题,5 + 5 + 10分,共计20分)
一、单选题
Which index can not support positional queries and phrase queries?
A.Biword index B.Phrase index
C.Positional index D.K-gram index
Which of the following statements about index partitioning is invalid?
A.Distributed index is partitioned across several machines in search engine, either according to term or according to document.
B.In the local inverted file (IFL) organization, each node is responsible for a disjoint subset of pages in the collection. A search query is broadcast to
all the nodes, each of which returns disjoint lists of page identifiers containing the search terms.
C.Global inverted file (IFG) organization partitions on index terms so that each query server stores inverted lists only for a subset of the terms in the
collection. A search query that asks for pages containing the specified term only involves node storing corresponding term.
D.The IFG strategy can be resilient to node failures and reduced network load. Performance studies also indicate that IFG organization uses system resources
effectively and provides good query throughout in most cases.
二、简答题
types of tolerant retrieval
SMART notation
the principle of index
the common process of relevance feedback
the underlying theory of Rocchio algorithm
assessment in evaluation of information retrieval systems
the characteristics of vertical search engine
the differences of vertical search and broad-based search
dangling links in PageRank algorithm
the relation of authorities and hubs in HITS algorithm.
the differences of XML retrieval and relational databases retrieval
the data model types of XML based on tree
三、计算题
扩展布尔检索、VSM和PageRank
四、案例题
A Weighted-Profiling Using an Ontology Base for Semantic-Based Search