DOC PREVIEW
Berkeley COMPSCI 61A - Lecture 37

This preview shows page 1 out of 2 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 2 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 2 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

61A Lecture 37Friday, December 2What is Computer Science?SystemsArtificial IntelligenceGraphicsSecurityNetworkingProgramming Languages...2Computer VisionPlanningRoboticsNatural Language Processing...Machine Translation3I will do it laterTarget languageParallel corpus gives translation examplesYo lo haré de muy buen gradoI will do it gladlyDespués lo verasYou will see laterMachine translation system:Model of translationTarget language corpus gives examples of well-formed sentencesI will get to it laterSee you laterHe will do itYo lo haré despuésNOVEL SENTENCESource languageThe Syntactic Structure of Natural Language4VBMD VPVPNPSPRP ADVYo lo haré de muy buen gradoI will do it gladlyDespués lo verasYou will see laterPRPVBMD VPVPNPSPRPADVI will do it laterModel of translationYo lo haré despuésMachine translation system:SSADVADVParallel corpus gives translation examplesA Translation System in 20 MinutesContext-free grammars as a model of language generationLarge-scale linguistic annotationsTree transformations5English Yoda-speakHelp you, I can! Yes! Mm!When 900 years old you reach, look as good, you will not. Hm.A Context-Free Grammar Describes Generation6 S -> NP VPNP -> PRPPRP!NP -> IVP -> VBVP -> VB PRPPRP -> you VB -> know VB -> help"Grammar""Lexicon"SNP VPPRP VB PRPI know youGrammar refinement!VPPRP!VP -> mePRP -> I!NP!VPA Context-Free Grammar Describes Generation7 S -> NP VPNP -> PRPPRP -> IVP -> VBVP -> VB PRPPRP -> youVP -> MD VP VB -> know VB -> help MD -> can"Grammar""Lexicon"SNP VPPRPIA grammar can be learned from data (demo)canMDVPVB PRPhelp youLeft cornersLeft-Corner Parsing Builds Trees For Sentences8 S -> NP VPNP -> PRPPRP -> IVP -> VBVP -> VB PRPPRP -> you VB -> know VB -> help"Grammar""Lexicon"Siknow youNPPRPVBcomplete(VP, (VP (VB know)), 2)VPparse_next(S, 1)complete(S, (PRP i), 1)complete(S, (NP (PRP i)), 1)parse_next(VP, 2)complete(VP, (VB know), 2)complete(S, (S ...), 1)Left-Corner Parsing Builds Trees For Sentences9 S -> NP VPNP -> PRPPRP -> IVP -> VBVP -> VB PRPPRP -> you VB -> know VB -> help"Grammar""Lexicon"SNPPRPVBiknow youVPPRPLeft cornerscomplete(VP, (VP (VB know) (PRP you)), 2)parse_next(S, 1)complete(S, (PRP i), 1)complete(S, (NP (PRP i)), 1)parse_next(VP, 2)complete(VP, (VB know), 2)complete(S, (S ...),


View Full Document

Berkeley COMPSCI 61A - Lecture 37

Documents in this Course
Lecture 1

Lecture 1

68 pages

Midterm

Midterm

5 pages

Midterm

Midterm

6 pages

Lecture 35

Lecture 35

250 pages

Lecture 14

Lecture 14

125 pages

Lecture 2

Lecture 2

159 pages

Lecture 6

Lecture 6

113 pages

Lecture 3

Lecture 3

162 pages

Homework

Homework

25 pages

Lecture 13

Lecture 13

117 pages

Lecture 29

Lecture 29

104 pages

Lecture 11

Lecture 11

173 pages

Lecture 7

Lecture 7

104 pages

Midterm

Midterm

6 pages

Midterm

Midterm

6 pages

Lecture 8

Lecture 8

108 pages

Lab 4

Lab 4

4 pages

Lecture 7

Lecture 7

52 pages

Lecture 20

Lecture 20

129 pages

Lecture 15

Lecture 15

132 pages

Lecture 9

Lecture 9

95 pages

Lecture 30

Lecture 30

108 pages

Lecture 17

Lecture 17

106 pages

Load more
Download Lecture 37
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Lecture 37 and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Lecture 37 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?