1 / 57

AI Seminar

AI Seminar. Our web page is at: www.cs.nmsu.edu/~gradrep Under “Events” in left frame. Identifying Ideological Point of View. Melanie Martin August 29, 2001. Outline of this presentation. What is AI??? Introduction and Motivation The proposed system Ideology Discourse

kelli
Download Presentation

AI Seminar

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. AI Seminar Our web page is at: www.cs.nmsu.edu/~gradrep Under “Events” in left frame Melanie Martin - AI Seminar

  2. Identifying Ideological Point of View Melanie Martin August 29, 2001 Melanie Martin - AI Seminar

  3. Outline of this presentation • What is AI??? • Introduction and Motivation • The proposed system • Ideology • Discourse • Statistical NLP and Machine Learning • Internet • Conclusion Melanie Martin - AI Seminar

  4. What is AI??? • “The practice of designing systems that possess and acquire knowledge and reason with knowledge.” (Tanimoto 1987) • “The design and study of computer programs that behave intelligently.” (Dean, Allen, Aloimonos 1995) • “The branch of computer science concerned with making computers behave like humans.” (Webopedia) Melanie Martin - AI Seminar

  5. What is AI??? • But then, what is intelligence??? • “the capacity for learning, reasoning, understanding, and similar forms of mental activity; aptitude in grasping truths, relationships, facts, meanings, etc.” (Webster’s Encyclopedic Unabridged Dictionary of the English Language 1996) Melanie Martin - AI Seminar

  6. Agents Data Mining Expert Systems Games and Search Knowledge Representation Machine Learning Theory, Case-Based, Rule Learning, ... Natural Language Processing Planning Robotics Speech Theorem Proving Vision & Pattern Recognition What is AI??? Categories under AI on Cora http://cora.whizbang.com/ Melanie Martin - AI Seminar

  7. What is AI??? • Goals in AI • Engineering: Solve real-world problems. Build systems that exhibit intelligent behavior. • Scientific: Understand what kind of computational mechanisms and knowledge are needed for modeling intelligent behavior. Melanie Martin - AI Seminar

  8. What is AI??? • Do we really want to model humans? • Seem like our best example, but…. • Should we build airplanes with wings that flap like birds? • How do we know we did it? • Turing test? • Focus on behavior instead of internal algorithm • Defines success in terms of human intelligence • Not well founded Melanie Martin - AI Seminar

  9. What is AI??? • A couple of recurring issues: • How important is cognitive modeling in our systems? • How do we balance scientific and engineering goals? • How do we evaluate our system? Melanie Martin - AI Seminar

  10. What is AI??? • So let’s get to the system we want to talk about today….. • This system will be in the area of Natural Language Processing aka Computational Linguistics Melanie Martin - AI Seminar

  11. Outline of this presentation • What is AI??? • Introduction and Motivation • The proposed system • Ideology • Discourse • Statistical NLP and Machine Learning • Internet • Conclusion Melanie Martin - AI Seminar

  12. Introduction and Motivation • Your back hurts, so you go to the web to find out what you can do, but there is too much information! • You are still bothered by the Florida election results and want to read a few sample articles with differing points of view. How can you find them? Melanie Martin - AI Seminar

  13. Introduction and Motivation • Suppose we could take information from web pages and Usenet newsgroups on a given topic and segment, classify or cluster it by ideological point of view….. • This talk is about what it might take to develop such a system. Melanie Martin - AI Seminar

  14. Introduction and Motivation • Sounds like a cool toy, but would it make any research contribution? • Areas where it could contribute: • natural language understanding • information retrieval • information extraction • internet structure Melanie Martin - AI Seminar

  15. Introduction and Motivation • But will it save the world? • Maybe not, but there is social value in analyzing ideological point of view • find implicit ideological content • better informed, more rational discussion of important issues Melanie Martin - AI Seminar

  16. Outline of this presentation • What is AI??? • Introduction and Motivation • The proposed system • Ideology • Discourse • Statistical NLP and Machine Learning • Internet • Conclusion Melanie Martin - AI Seminar

  17. The Proposed System • Let’s recall what we want to do: • Build a system that could take information from web pages and Usenet newsgroups on a given topic and segment, classify or cluster it by ideological point of view….. Melanie Martin - AI Seminar

  18. The Proposed System User inputs topic Ideological Classifier Search Engine Topic Classifier, Filter Set of documents on topic Internet: Web pages, Usenet Docs on topic classified by IPV Melanie Martin - AI Seminar

  19. The Proposed System • Immediately some issues arise: • Can we come up with a definition of ideological point of view that is computationally feasible? • To what extent do we need to understand the text? • Would modeling human text understanding help? Melanie Martin - AI Seminar

  20. The Proposed System • More issues: • Can the structure of the internet help us? • What kind of knowledge is needed and can it be learned? • How are we going to evaluate our system? Melanie Martin - AI Seminar

  21. Outline of this presentation • What is AI??? • Introduction and Motivation • The proposed system • Ideology • Discourse • Statistical NLP and Machine Learning • Internet • Conclusion Melanie Martin - AI Seminar

  22. Ideology • Working definition from van Dijk: “Ideologies are the fundamental beliefs of a group and its members.” • No negative evaluation • Subjective, since beliefs are subjective • Discourse plays a key role in development and promulgation of ideologies Melanie Martin - AI Seminar

  23. Ideology • What do we mean by groups? • More than one person • Fewer than the entire society or culture • Some level of permanency or common goals • Some membership criteria • Member identification with the group • Basis for self-definition and commonality • Structure, possibly informal Melanie Martin - AI Seminar

  24. Ideology • General strategy of most ideological discourse (van Dijk’s Ideological Square): • Emphasize positive things about Us • Emphasize negative things about Them • De-emphasize negative things about Us • De-emphasize positive things about Them • Polarization; Us versus Them Melanie Martin - AI Seminar

  25. Ideology • How are these strategies instantiated in discourse? • What is there: • argument structure • syntactic patterns • style and non-literal language • actor descriptions • thematic structure • topoi Melanie Martin - AI Seminar

  26. Ideology • What is not there • implication • presupposition • inference • goals and plans Melanie Martin - AI Seminar

  27. Ideology • Disclaimers, selected examples: • Apparent Negation: I have nothing against X, but... • Apparent Concession: They may be very smart, but... • Apparent Empathy: They may have had problems, but... • Apparent Effort: We do everything we can, but... • Positive self-representation and face keeping Melanie Martin - AI Seminar

  28. Ideology • Linguistics • van Dijk (1998) • Blommaert & Verschueren (1998) • Wang (1993) • Wortham & Locher (1996) Melanie Martin - AI Seminar

  29. Ideology • The Systems • Ideology Machine -1965 to 1973 - Abelson et al. • Tale-Spin - 1976 - Meehan • Politics - 1979 - Carbonell • Pauline - 1987 - Hovy • Viewgen - 1991 - Ballim & Wilks • Tracking Point of View in Narrative - 1994 - Wiebe • Spin Doctor - 1994 - Sack • Terminal Time - 2000 - Mateas et al. Melanie Martin - AI Seminar

  30. Ideology • Some issues • Evaluation!!! • Hard-coded knowledge • Domain dependence • Cognitive plausibility • More precise definitions Melanie Martin - AI Seminar

  31. Ideology • What do we want to take with us? • van Dijk’s definitions augmented by Sack and Wiebe • mine everything for clues to ideological point of view Melanie Martin - AI Seminar

  32. Outline of this presentation • What is AI??? • Introduction and Motivation • The proposed system • Ideology • Discourse • Statistical NLP and Machine Learning • Internet • Conclusion Melanie Martin - AI Seminar

  33. Discourse • Now that we have a working definition of ideology and some ideas about things that might be clues, the question becomes how to find them? • First we are going to look at theories of discourse structure that might be useful. Melanie Martin - AI Seminar

  34. Discourse • Computational Linguistics • Hobbs (1979) • Mann & Thompson (RST) (1988) • Grosz & Sidner (G&S) (1986) • Morris & Hirst (Lexical chains) (1991) • Psycholinguistics • Kintsch (1994) Melanie Martin - AI Seminar

  35. Discourse • Issues • do we need it at all? • implementation • Hobbs, G&S, RST • finite number of fixed primitives • Hobbs, RST • world knowledge • Hobbs • domain specific Melanie Martin - AI Seminar

  36. Discourse • A reasonable first approach: Lexical Chains (Morris & Hirst) • Sequences of related words spanning a topical unit in the text • based on lexical cohesion • encapsulates context • helps identify key phrases Melanie Martin - AI Seminar

  37. Discourse • Lexical chains could help us in: • topic segmentation • intentional structure • lexical features for a classifier Melanie Martin - AI Seminar

  38. Discourse • Lexical chains are easy to implement, but are unlikely to be sufficient… • For the next approximation: RST • Marcu’s implementation incorporating G&S • Mostly used for summarization and generation • Would help get at the argument structure of the text Melanie Martin - AI Seminar

  39. Discourse • Would most likely use RST to generate features for a classifier or as input to a pattern recognizer • Nuclei spans help pick out the more important segments of text • Produces a tree that gives the structure of the rhetorical structure of the text Melanie Martin - AI Seminar

  40. Discourse • None of the discourse theories look like the are going to stand alone • may be able to give us structural, lexical and other features • need to consider classification or clustering based on these features • so we turn to…. Melanie Martin - AI Seminar

  41. Outline of this presentation • What is AI??? • Introduction and Motivation • The proposed system • Ideology • Discourse • Statistical NLP and Machine Learning • Internet • Conclusion Melanie Martin - AI Seminar

  42. Statistical NLP and ML • Two techniques we will consider • Latent Semantic Analysis • Probabilistic Classification Melanie Martin - AI Seminar

  43. Statistical NLP and ML • Issues • clustering versus classification • categories may not be predefined • may want to take a variety of features into account • favor learning over hard-coding knowledge • supervised versus unsupervised • cost of annotated training data Melanie Martin - AI Seminar

  44. Statistical NLP and ML • Latent Semantic Analysis • text represented as a matrix • entries are weighted frequency of word in context • semantic space obtained through SVD • words appearing in similar context have similar feature vectors • characterizes semantic content of words in context Melanie Martin - AI Seminar

  45. Statistical NLP and ML • Why LSA is a good choice here • semantics is key component of ideological discourse • clustering without need for predefined categories • already shown useful for: • summarization (Ando 2000) • text segmentation (Choi 2001) • measuring text coherence (Foltz 1998) Melanie Martin - AI Seminar

  46. Statistical NLP and ML • But LSA doesn’t use all of the stuff we just spent all this time talking about… • What if it doesn’t work very well? • Another option is a probabilistic classifier • assigns most probable class to an object bases on a probability model Melanie Martin - AI Seminar

  47. Statistical NLP and ML • Probability model • defines joint distribution of variables • set of feature variables and a class variable • Wiebe and Bruce (1995) got around the issue of not knowing the classes in advance by breaking up the problem and using a series of classifiers Melanie Martin - AI Seminar

  48. Statistical NLP and ML • Maybe this will work after all and we can use some of the features we have been talking about • Deciding which features to use can be determined statistically with goodness of fit of graphical models Melanie Martin - AI Seminar

  49. Statistical NLP and ML • Both methods seem to have a lot of potential • LSA would be easier to implement • possibly a baseline for evaluation of probabilistic classifiers • Less linguistic knowledge gain likely with LSA Melanie Martin - AI Seminar

  50. Outline of this presentation • What is AI??? • Introduction and Motivation • The proposed system • Ideology • Discourse • Statistical NLP and Machine Learning • Internet • Conclusion Melanie Martin - AI Seminar

More Related