1 / 25

Information Retrieval

Information Retrieval. Take a query and a set of documents. Select the subset of documents (or parts of documents) that match the query Statistical approaches Look at things like word frequency More knowledge based approaches interesting, but maybe not helpful. Information Extraction.

beck-huff
Download Presentation

Information Retrieval

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. Information Retrieval • Take a query and a set of documents. • Select the subset of documents (or parts of documents) that match the query • Statistical approaches • Look at things like word frequency • More knowledge based approaches interesting, but maybe not helpful

  2. Information Extraction • From a set of documents, extract “interesting” pieces of data • Hand-built systems • Learning pieces of the system • Learning the entire task (for certain versions of the task) • Wrapper Induction

  3. IE Demo • http://www.smi.ucd.ie/bwi/

  4. Question Answering • Given a question and a set of documents (possibly the web), find a small portion of text that answers the question. • Some work on putting answers together from multiple sources.

  5. QA Demos • http://qa.wpcarey.asu.edu/

  6. Text Mining • Outgrowth of data mining. • Trying to find “interesting” new facts from texts. • One approach is to mine databases created using information extraction.

  7. Pragmatics • Distinctions between pragmatics and semantics get blurred in practical systems • To be a practically useful system, some aspects of pragmatics must be dealt with, but we don’t often see people making a strong distinction between semantics and pragmatics these days. • Instead, we often distinguish between sentence processing and discourse processing

  8. What Kinds of Discourse Processing Are There? • Anaphora Resolution • Pronouns • Definite noun phrases • Handling ellipsis • Topic • Discourse segmentation • Discourse tagging (understanding what conversational “moves” are made by each utterance)

  9. Approaches to Discourse • Hand-built systems that work with semantic representations • Hand-built systems that work with text (or recognized speech) or parsed text • Learning systems that work with text (or recognized speech) or parsed text

  10. Issues • Agreement on representation • Annotating corpora • How much do we use the modular model of processing?

  11. Summarization • Short summaries of a single text or summaries of multiple texts. • Approaches: • Select sentences • Create new sentences (much harder) • Learning has been used some but not extensively

  12. Machine Translation • Best systems must use all levels of NLP • Semantics must deal with the overlapping senses of different languages • Both understanding and generation • Advantage in learning: bilingual corpora exist--but we often want some tagging of intermediate relationships • Additional issue: alignment of corpora

  13. Approaches to MT • Lots of hand-built systems • Some learning used • Probably most use a fair bit of syntactic and semantic analysis • Some operate fairly directly between texts

  14. Generation • Producing a syntactically “good” sentence • Interesting issues are largely in choices • What vocabulary to use • What level of detail is appropriate • Determining how much information to include

  15. Strong vs. Weak AI • “Weak” AI • Claims that the digital computer is a useful tool for studying intelligence and developing useful technology. • A running AI program is at most a simulation of a cognitive process but is not itself a cognitive process. • Analogously, a meteorological computer simulation of a hurricane is not a hurricane. • “Strong” AI • Claims that a digital computer can in principle be programmed to actually BE a mind, to be intelligent, to understand, perceive, have beliefs, and exhibit other cognitive states normally ascribed to human beings.

  16. Ethical issues in AI • What are the benefits and risks in attempting to develop AI programs?

  17. Can Machines Act Intelligently? • The Turing test

  18. Argument from informality • Human behavior is far too complex to be captured by any simple set of rules, and computer can only follow sets of rules, so computer cannot generate behavior as intelligent as that of humans.

  19. Issues Raised • Need for background knowledge to achieve good generalization from examples • Learning should be possible without a teacher. • Learning should be possible in the face of a multitude of features. • Intelligent agents should be able to look for relevant information.

  20. Could machines ever really think? • The mind-body problem • Dualist • Monist or materialist

  21. Problems with dualism • Are you willing to accept the existence of an immaterial soul? • Note that the concept of the brain as hardware and the mind as software is a dualist concept.

  22. Problems with materialism • Free will. • Consciousness

  23. Thought Experiments • Brain in a vat • Brain prosthesis • The Chinese room

  24. Argument from disability • What is this? • What responses can we make?

  25. Gödel's Incompleteness Theorem • Not necessarily applicable to computers, which aren’t really Turing machines. • Being able to establish mathematical truth may not be the same as acting intelligently. • Humans are inconsistent in their thinking.

More Related