Vector-Space Model and Term-Document Matrix Quiz

Terms in the Vector-Space Model are called index terms or vocabulary terms.

Each term in a document is assigned a complex-valued weight, wij.

In the Term-Document Matrix, zero weight for a term indicates it is highly significant in the document.

Term Frequency measures how common a term is across documents.

Inverse Document Frequency (IDF) increases for terms that are common across many documents.

The more frequent a word is used across documents, the higher its IDF score.

In Boolean Retrieval Model, it is easy to control the number of documents retrieved.

A bag of words representation allows for multiple occurrences of the same word.

In Statistical Models, documents are typically represented by ordered sequences of words.

In the term-document matrix representation, rows represent terms and columns represent documents.

Similarity between a document and a query in the Vector Space Model is determined based on the length of the document.

Determining important words in a document is one of the issues addressed by the Vector Space Model.

A retrieval model specifies the details of document representation, query representation, and retrieval function.

Statistical models are the only type of retrieval models mentioned in the text.

In the Boolean Model, a document is represented as a collection of phrases.

One of the preprocessing steps includes converting tokens to their plural forms for accurate indexing.

Filtering tasks involve varied queries on a continuous document stream.

Ad hoc retrieval tasks involve a fixed document corpus with fixed queries.