Курсы английского
<<  Conditions for Divergence and Convergence in the Micro-Evolution of Language Estimating the Selectivity of XML Path Expressions for Internet Scale Applications  >>
Natural Language Processing for the Web
Natural Language Processing for the Web
Logistics
Logistics
Today
Today
Sentence extraction
Sentence extraction
Background
Background
Today’s systems
Today’s systems
Karen Sparck Jones Automatic Summarizing: Factors and Directions
Karen Sparck Jones Automatic Summarizing: Factors and Directions
Sparck Jones claims
Sparck Jones claims
Questions (from Sparck Jones)
Questions (from Sparck Jones)
For the next two classes
For the next two classes
Trimmer Algorithm
Trimmer Algorithm
Headline Ambiguity
Headline Ambiguity

Презентация: «Natural Language Processing for the Web». Автор: Kathleen McKeown. Файл: «Natural Language Processing for the Web.pptx». Размер zip-архива: 183 КБ.

Natural Language Processing for the Web

содержание презентации «Natural Language Processing for the Web.pptx»
СлайдТекст
1 Natural Language Processing for the Web

Natural Language Processing for the Web

Prof. Kathleen McKeown 722 CEPSR, 939-7118 Office Hours: Wed, 1-2; Mon 3-4 TA: Fadi Biadsy 702 CEPSR, 939-7111 Office Hours: Thurs 6-8

2 Logistics

Logistics

Remaining classes CS Conference Room Except April 3rd, back in 223 Mudd Invited speakers: 7th Floor Interschool Lab CS account: apply for one now http://www.cs.columbia.edu/crf/accounts Presentations, Discussants Need two presenters for next week If you haven’t already signed up, sign up on sheet going around

3 Today

Today

Overview Single doc summarization systems: Trimmer (Zajic et al), Kathy Cut and Paste (Jing and McKeown), Sigfried Gold Statistical Sentence Compression (Knight and Marcu), Kathy Tools Parsers, POS taggers, Barry Schiffman Evaluation Pyramids (Nenkova and Passonneau), Joshua Nankin Rouge (Lin and Hovy), Kathy

4 Sentence extraction

Sentence extraction

Sparck Jones: `what you see is what you get’, some of what is on view in the source text is transferred to constitute the summary

5 Background

Background

Sentence extraction the main approach Some more sophisticated features for extraction Lexical chains, anaphoric reference Machine learning model for learning an extraction summarizer: Kupiec, SIGIR 95.

6 Today’s systems

Today’s systems

How can we edit the selected text?

7 Karen Sparck Jones Automatic Summarizing: Factors and Directions

Karen Sparck Jones Automatic Summarizing: Factors and Directions

8 Sparck Jones claims

Sparck Jones claims

Need more power than text extraction and more flexibility than fact extraction (p. 4) In order to develop effective procedures it is necessary to identify and respond to the context factors, i.e. input, purpose and output factors, that bear on summarising and its evaluation. (p. 1) It is important to recognize the role of context factors because the idea of a general-purpose summary is manifestly an ignis fatuus. (p. 5) Similarly, the notion of a basic summary, i.e., one reflective of the source, makes hidden fact assumptions, for example that the subject knowledge of the output’s readers will be on a par with that of the readers for whom the source was intended. (p. 5) I believe that the right direction to follow should start with intermediate source processing, as exemplified by sentence parsing to logical form, with local anaphor resolutions

9 Questions (from Sparck Jones)

Questions (from Sparck Jones)

Does subject matter of the source influence summary style (e.g, chemical abstracts vs. sports reports)? Should we take the reader into account and how? Is the state of the art sufficiently mature to allow summarization from intermediate representations and still allow robust processing of domain independent material?

10 For the next two classes

For the next two classes

Consider the papers we read in light of Sparck Jones’ remarks on the influence of context: Input Source form, subject type, unit Purpose Situation, audience, use Output Material, format, style

11 Trimmer Algorithm

Trimmer Algorithm

12 Headline Ambiguity

Headline Ambiguity

Iraqi Head Seeks Arms Juvenile Court to Try Shooting Defendant Teacher Strikes Idle Kids Kids Make Nutritious Snacks British Left Waffles on Falkland Islands Red Tape Holds Up New Bridges Bush Wins on Budget, but More Lies Ahead Hospitals are Sued by 7 Foot Doctors Ban on nude dancing on Governor’s desk Local high school dropouts cut in half

«Natural Language Processing for the Web»
http://900igr.net/prezentacija/anglijskij-jazyk/natural-language-processing-for-the-web-145439.html
cсылка на страницу

Курсы английского

25 презентаций о курсах английского
Урок

Английский язык

29 тем
Слайды