Three major component of Information Retrieval system are document subsystem ,Retrieval Subsystem and

is the unit of information that we want to return as a result of

is the topic about which the user desires to know more

is the smallest unit of information in a query

Permuterm index is a index form of index

A Query like mon is called as wildcard query

algorithm is the algorithm for phonetic hashing

Edit distance type of spelling correction is

In Permuterm index symbol is used to mark the end of a term

is fraction of returned result relevant to information need

Within Documernt collection each document has unique serial number known as

is the process of selecting how to organize the work of answering a query so that least amount of work need to be done by system

is a model for information retrieval in which we can pose any query which is in the form of Boolean Expression of terms

is a fraction of relavant documents in the collection were returned by the system

The idea to use computers for searching information was published in the article As We May Think by 1945 in

is the data structure for faster information retrieval which is collection of selected words and associated pointers

were the first to adopt Information retrival system for retriving information

In Document subsystem Abstracting contains

In Document Subsystem file organization contains term by term list of records under each term is called as

IR Stands for______________.

Each item in the list is called as______________.

etr term is called _________k-grams wildcard query.

To search document by _______________ in IR.

SEO stands for _____________ .

Dictionary performed by _________________pair

An advantage of a positional index is that it reduces the asymptotic complexity of a postings intersection operation.

_________can best be described as a programming model used to develop Hadoopbased applications that can process massive amounts of data.

The purpose of the inverse document frequency is to increase the weight of terms with high collection frequenc.

URL Stands for ______________________.

A data structure that maps terms back to the parts of a document in which they occur is called an

The first large information retrieval research group was formed by____________at cornell in 1960.

Input, Purpose and Output are the factors of _________ .

A deadlock can be broken down by

NLTK stands for ______________ .

A model of information retrieval in which we can pose any query in which search terms are combined with the operators AND, OR, and NOT:

A data structure that maps terms back to the parts of a document in which they occur is called an (select the best answer):

A process to efficiently intersect lists to be able to quickly find documents that contain both terms is referred to as merging postings lists.

The model of information retrieval in which we can pose any query in the form of a Boolean expression is called the ranked retrieval model.

The number of times that a word or term occurs in a document is called the:

Stemming increases the size of the vocabulary.

In information retrieval, extremely common words which would appear to be of little value in helping select documents that are excluded from the index vocabulary are called:

A crude heuristic process that chops off the ends of the words to reduce inflectional forms of words and reduce the size of the vocabulary is called:

An advantage of a positional index is that it reduces the asymptotic complexity of a postings intersection operation.

An index that includes sequences of words or terms of variable length that have been extracted from a source document is called a:

One disadvantage, as outlined in our text, of using a permuterm index for wild card queries is:

Which of the following is a technique for context sensitive spelling correction:

For a very large collection of books of classic literature the most appropriate indexing algorithm would be:

For a large collection of documents such as the internet that experience frequent change the most appropriate indexing algorithm would be:

Given two strings s1 and s2, the edit distance between them is sometimes known as the:

For a moderately large collection of static documents maintained on a single system the most appropriate indexing algorithm would be:

For a small collection of documents on a personal computer that don't experience any change the most appropriate indexing algorithm would be:

Hashing is a process where an item is reduced, through a mathematical process, to an integer.

The size of the document collection that can be indexed by single-pass in-memory indexing algorithm is limited by the size of the disk storage the computer running the indexer process has access to.

The formula used to estimate the vocabulary size of a collection is known as:

Which of the following is NOT a benefit of index compression?

A compression algorithm that results in some loss of data is called:

An approach to compression that takes advantage of the redundancy in the dictionary that results from common prefixes that come from sorted terms is called:

A disadvantage of compression is that it reduces the transfer of data from disk to memory.

The 30 most common words account for 30% of the tokens in written text is known as front coding.

Weighted zone scoring is sometimes referred to as ranked Boolean retrieval.

In the bag of words model, the exact ordering of terms within the document is both significant and relevant to processing.

The purpose of the inverse document frequency is to increase the weight of terms with high collection frequency.

A scheme where a weight is assigned to a term based upon the number of occurrences of the term within a document is called:

The number of documents within a collection that contain a particular term is the collection frequency of the term.

A metric derived by taking the log of N divided by the document frequency where N is the total number of documents in a collection is called:

The tf-idf weight is highest when a term t occurs many times within a small number of documents.

The tf-idf weight is lower when a term t occurs many times in a document or occurs in relatively few documents.

A measure of similarity between two vectors which is determined by measuring the angle between them is called:

An index that is often supplemental to the inverted index and contains terms from only a particular field or section of a document is called a parametric index.

An approach to retrieval in a search that is likely (but not precisely) to produce the top K scoring documents is called:

An approach to computing scores in an IR system that pre-computes for each term in the dictionary, the set of documents with the highest weights for the term is:

An approach to computing scores in an IR system that orders documents in the posting list of a term by decreasing order of term frequency is called:

An approach to computing scores in an IR system that selects a sample of documents randomly from the collection as leaders which are in the index and links similar documents to it (followers) is called:

Which of the following items is not a component of a complete search system?

Which of the following is NOT one of the types of queries in a complete search system discussed in our text?

Considering only documents containing terms whose idf exceeds a preset threshold is an index elimination.

A scoring function that computes an aggregate of a document's relevance from multiple sources is called evidence accumulation.

A scheme where a weight is assigned to a term based upon the number of occurrences of the term within a document is called:

A group of related documents against which information retrieval is employed is called:

Weighted zone scoring is referred to as:

An approach to compression that takes advantage of the redundancy in the dictionary that results from common prefixes that come from sorted terms is called:

True/False: Given two strings s1 and s2, the edit distance between them is sometimes known as the Levenshtein distance.

True/False: Ad hoc retrieval is a model of information retrieval in which we can pose any query in which search terms are combined with the operators AND, OR, and NOT.

True/False: An advantage of compression is that it reduces the transfer of data from disk to memory.

True/False: The process where multiple lists are evaluated using AND or OR operators in a Boolean retrieval query is called an intersection operation.

For a small collection of documents on a personal computer that don't experience any change the most appropriate indexing algorithm would be:

True/False: The number of documents within a collection that contain a particular term is the collection frequency of the term.

The number of times that a word or term occurs in a document is called the:

True/False: In the bag of words model, the exact ordering of terms within the document is not relevant to processing.

True/False: The Jaccard algorithm is a technique for context sensitive spelling correction.

True/False: Precision in an information retrieval system refers to the fraction of relevant documents in the collection that were returned by the system.

True/False: The purpose of the inverse document frequency is to increase the weight of terms with high collection frequency.

In information retrieval, extremely common words which would appear to be of little value in helping select documents that are excluded from the index vocabulary are called:

A process that reduces the size of a vocabulary by reducing to the 'root' of words is called:

A compression algorithm that results in some loss of data is called:

Which of the following is NOT a benefit of index compression?

True/False: tf-idf weight is a metric derived by taking the log of N divided by the document frequency where N is the total number of documents in a collection.

True/False: Vector similarity is a measure of similarity between two vectors which is determined by measuring the angle between them.

True/False: Heap's law is the formula used to estimate the vocabulary size of a collection is.

To evaluate the effectiveness of an IR system the output from a standard query executed against the test IR system is compared with the known output from a:

Precision is the fraction of retrieved documents that are relevant.

Recall is the fraction of non relevant documents that are retrieved.

Accuracy is typically the most accurate measure of IR system effectiveness.

The F-measure is a single measure that balances precision versus recall.

The purpose of the inverse document frequency is to increase the weight of terms with high collection frequency.

The standard approach to information retrieval system evaluation involves around the notion of:

A web server communicates with a client (browser) using which protocol:

The basic operation of a web browser is to pass a request to the web server. This request is an address for a web page and is known as the:

A web page whose content doesn't vary from one request to another is called a:

A web link within a web page that references another part of the same page is called a:

In the context of web search engines the manipulation of web page content for the purpose of appearing high up in search results for selected query terms is called:

Results from a search engine that are based upon the retrieval of items using a method of term weighting such as cosine similarity is a form of:

A program that captures and indexes content from web pages is known as what insect:

The list of web pages that a web crawler has queued up to index is called the:

In order to access a particular web site in the internet, the URL must be converted into an IP address. Which service does this conversion?

A model of information retrieval in which we can pose any query in which search terms are combined with the operators AND, OR, and NOT:

A data structure that maps terms back to the parts of a document in which they occur is called an (select the best answer):

A process to efficiently intersect lists to be able to quickly find documents that contain both terms is referred to as merging postings lists.

The model of information retrieval in which we can pose any query in the form of a Boolean expression is called the ranked retrieval model.