1 / 29

ISP 433/533 Week 2

ISP 433/533 Week 2. IR Models. Outline. IR defined IR tasks IR processes Boolean model Break Vector space model Probabilistic model. User Information Needs. Goal of IR Hard Problem People have different and highly varied needs for information

rane
Download Presentation

ISP 433/533 Week 2

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. ISP 433/533 Week 2 IR Models

  2. Outline • IR defined • IR tasks • IR processes • Boolean model • Break • Vector space model • Probabilistic model

  3. User Information Needs • Goal of IR • Hard Problem • People have different and highly varied needs for information • People often do not know what they want, or may not be able to express it in a usable form

  4. Some Definitions of IR Salton (1989): “Information-retrieval systems process files of records and requests for information, and identify and retrieve from the files certain records in response to the information requests. The retrieval of particular records depends on the similarity between the records and the queries, which in turn is measured by comparing the values of certain attributes to records and information requests.” Kowalski (1997): “An Information Retrieval System is a system that is capable of storage, retrieval, and maintenance of information. Information in this context can be composed of text (including numeric and date data), images, audio, video, and other multi-media objects).”

  5. Examples of IR • Conventional (library catalog). Search by keyword, title, author, etc. • Text-based (Lexis-Nexis, Google, FAST).Search by keywords. Limited search using queries in natural language. • Multimedia (QBIC, WebSeek, SaFe)Search by visual appearance (shapes, colors,… ). • Question answering systems (AskJeeves, NSIR, Answerbus)Search in (restricted) natural language

  6. Key Terms Used in IR • QUERY: a representation of what the user is looking for - can be a list of words or a phrase. • DOCUMENT: an information entity that the user wants to retrieve • COLLECTION: a set of documents • INDEX: a representation of information that makes querying easier • TERM: word or concept that appears in a document or a query • RANKING: an ordering of the documents retrieved that (hopefully) reflects the relevance of the documents to the user query

  7. Index Terms doc match Ranking Information Need query Basic IR Process Docs

  8. IR Task – ad hoc Q1 Q2 Collection -relatively stable Q3 Q4 Q5

  9. Docs Filtered for User 2 User 2 Profile User 1 Profile Docs for User 1 Documents Stream IR Task - filtering

  10. Process of IR User Interface Text operations Query operations DB Man. indexing Searching index Text Db Ranking

  11. Document Process Steps

  12. Classic IR models • Each document represented by a set of representative keywords or index terms • Not all terms are equally useful for representing the document contents: less frequent terms allow identifying a narrower set of documents • Let • kibe an index term • dj be a document • wijis a weight associated with (ki,dj) • The weight wij quantifies the importance of the index term for describing the document contents

  13. Boolean Model • Simple model based on set theory • Queries specified as boolean expressions • precise semantics • neat formalism using boolean logic • Eg. Queryx = ka (kb kc) • Terms are either present or absent. Thus, wij {0,1}

  14. Boolean Logic • Named after logician/mathematician George Boole • Logical Connectives: AND, OR, NOT • WARNING! • INSPIRED BY, BUT NOT THE SAME AS, USUAL ENGLISH USAGE AND: “Each thing must satisfy ALL conditions” OR : “Each thing must satisfy at least one condition” NOT: “Each thing must NOT satisfy the given condition”

  15. Logical AND () (Set Intersection) A  B is the set of things in common, i.e., in both sets A and B A B (Aged, Blind People) A B Aged Blind

  16. Logical OR () (Set Union) A  B is the set of: things in either A, B or both. A B (people that are either Aged or Blind or both) A B Aged Blind

  17. Logical NOT () (Set Complement)  B is the set of things outside the set B B (people who aren’t blind) B Blind

  18. Example Combination • A ( B) A ( B) (old people who aren’t blind) A B Blind Aged

  19. Exercise • D1 = “computer information retrieval” • D2 = “computer retrieval” • D3 = “information” • D4 = “computer information” • Q1 = “information retrieval” • Q2 = “information computer”

  20. Drawbacks of the Boolean Model • Retrieval based on binary decision criteria with no notion of partial matching • No ranking of the documents is provided (absence of a grading scale) • Information need has to be translated into a Boolean expression which most users find awkward • The Boolean queries formulated by the users are most often too simplistic • As a consequence, the Boolean model frequently returns either too few or too many documents in response to a user query • BREAK

  21. Vector Model • Non-binary weights provide consideration for partial matches • These term weights are used to compute a degree of similarity between a query and each document • Ranked set of documents provides for better matching

  22. Vector Space • Assume each term is independent from each other and each term defines a dimension • T-dimensional space, where T is the number of terms • In this space, queries and documents are represented as weighted vectors • Weight wiq >= 0 associated with the pair (ki,q) • vec(dj) = (w1j, w2j, ..., wtj) • vec(q) = (w1q, w2q, ..., wtq)

  23. Example Vector Space using term frequency • D1 = “computer information retrieval” • D2 = “computer retrieval” • Q1 = “information, retrieval” information Q1=(0, 1, 1) D1=(1, 1, 1) computer D2=(1, 0, 1) retrieval

  24. Similarity Measure • Sim(q,dj) = cos() = [vec(dj)  vec(q)] / ( |dj| * |q|) = [ wij * wiq] / (|dj| * |q|) • Since wij > 0 and wiq > 0, 0 <= sim(q,dj) <=1 j dj  q i

  25. Exercise • D1 = “computer information retrieval” • D2 = “computer retrieval” • Q1 = “information, retrieval” • Given the above query, rank the relevance of the above two documents using vector model

  26. Pro and Con of Vector model • Advantages: • term-weighting improves quality of the answer set • partial matching allows retrieval of docs that approximate the query conditions • cosine ranking formula sorts documents according to degree of similarity to the query • Disadvantages: • assumes independence of index terms (??); not clear that this is bad though

  27. Probabilistic Model • Given a user query, there is an ideal answer set • Querying as specification of the properties of this ideal answer set (clustering) • But, what are these properties? • Guess at the beginning what they could be (i.e., guess initial description of ideal answer set) • Improve by iteration

  28. Probabilistic Ranking Principle • Given a user query q and a document dj, the probabilistic model tries to estimate the probability that the user will find the document dj relevant • sim(q, dj ) = P(dj relevant-to q) / P(dj non-relevant-to q)

  29. Performance of Probabilistic Model • Salton and Buckley did a series of experiments that indicate that, in general, the vector model outperforms the probabilistic model with general collections • This seems also to be the view of the research community

More Related