chapter 6. inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실...
DESCRIPTION
Introduce(2/4) - Traditionally (GOFAI) serving deductive goals Valid inference Man (x) -> Mortal(x) Man(Socrates) Mortal(Socrates) Expressiveness Even first-order logic offers tradeoffs wrt/propositionalTRANSCRIPT
![Page 1: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/1.jpg)
Chapter 6. Inference beyond the index
2007 년 1 월 30 일부산대학교 인공지능연구실 김민호
Text : FINDING OUT ABOUTPage. 182 ~ 251
![Page 2: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/2.jpg)
Introduce(1/4) - Knowledge representation
AI is primary contribution to computer science! Related to:
Programming language’s “abstract data types” Database (logical!) modeling
- eg, ‘ontology’ building
![Page 3: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/3.jpg)
Introduce(2/4) - Traditionally (GOFAI) serving deductive goals
Valid inferenceMan (x) -> Mortal(x)
Man(Socrates)
Mortal(Socrates) Expressiveness
Even first-order logic offers tradeoffs wrt/propositional
![Page 4: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/4.jpg)
Introduce(3/4) - Machine learning: inductive sources of knowledge
Data-mining Statistical analysis of large datasets Searching for patterns
Inferring semantics (meaning) from syntactic cues from word statistics from bibliographic citations Even from capitalization
- Proper names → Global reference!
![Page 5: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/5.jpg)
Introduce(4/4) - Exploiting other (non-index) information
![Page 6: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/6.jpg)
Subsection
6.1 Citation: Interdocument Links6.2 Hypertext, Intradocument Links6.3 Keyword Structures6.4 Social Relations among Authors6.5 Modes of Inference6.6 Deep Interfaces6.7 FOA(The Law)6.8 FOA(Evolution)6.9 Text-Based Inteligence
![Page 7: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/7.jpg)
6.1 Citation: Interdocument Links
Citation is a pointer, from a document to a document. how accurately do we know the location of the
citation in the citing paper? how precisely is its pointer into the cited paper?
![Page 8: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/8.jpg)
6.1 Citation: Interdocument Links
Document similarity based on shared bibliographies Coupling
Overlap between two document’s bibliographis Co-citation
Degree to which two documents are both referenced by other document’s bibliographies
![Page 9: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/9.jpg)
6.1 Citation: Interdocument Links
![Page 10: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/10.jpg)
6.1 Citation: Interdocument Links
Common law depends on rule of precedence Stare decisis Prior decisions applied to new factual situations
Hierarchical local jurisdictions limit interpretation Dialectic debate (rationale, justice, change, etc.) NB: Same corpus used by both adversaries References to history of O(10 year)
![Page 11: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/11.jpg)
6.1 Citation: Interdocument Links
Unambiguous
![Page 12: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/12.jpg)
6.1 Citation: Interdocument Links
Eigen-structure of citation graphs
Authority: analogous to bibliometric ‘impact’
Hubs: Pull together authorities Citation-expanded hitlist
![Page 13: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/13.jpg)
Summary
Writings do not exist in isolation Author explicit references to other’s documents
provides excellent evidence concerning the ARGUMENTS they each make
![Page 14: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/14.jpg)
Google’s Page rank
Simulate stationary distribution of Markov process with incremental update of page weight
![Page 15: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/15.jpg)
Hierarchic structure
Visualizing references
![Page 16: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/16.jpg)
Pedagogical structure
Prerequisite lattice Reading-level analysis – against well – tested
vocabularies Level of coverage
![Page 17: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/17.jpg)
Argument relationships
![Page 18: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/18.jpg)
thesaurus
BT/NT/RT relations aot / AI “ontologies”
![Page 19: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/19.jpg)
WordNet
![Page 20: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/20.jpg)
Classification taxonomies
Institutionalized Myopic discipline
focus
![Page 21: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/21.jpg)
Neural networks - basicsQuery
Retrieval Relevance
Feedback
![Page 22: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/22.jpg)
Construction of initial NNet
![Page 23: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/23.jpg)
Query: “Case-based approach to the law”
Morphological processing of tokens High-frequency “noise” words elided
![Page 24: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/24.jpg)
SAS in IR
Initial query may refer to many “features” Descriptive keywords are
only one type Retrieval becomes a
process of completion
![Page 25: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/25.jpg)
Type of relation less important than fact of association
![Page 26: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/26.jpg)
Initial retrieval
![Page 27: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/27.jpg)
Most highly ranked document
![Page 28: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/28.jpg)
Goal document
![Page 29: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/29.jpg)
3rd-order transitive associations
![Page 30: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/30.jpg)
4th-order transitive associations
![Page 31: Chapter 6. Inference beyond the index 2007 년 1 월 30 일 부산대학교 인공지능연구실 김민호…](https://reader036.vdocuments.net/reader036/viewer/2022062505/5a4d1bcb7f8b9ab0599d6e4b/html5/thumbnails/31.jpg)
Swanson's Arrowsmith