Chapter 6 Natural Language Processing 1 NLP Language
- Slides: 31
Chapter 6 Natural Language Processing 1
NLP Language translation / multilingual translation n Language understanding n Figure 14. 5 p. 365 Interaction among component n Figure 14. 6 p. 366 A speech Waveform n 2 344 -471 AI & ES Chapter 6 NLP
NLP Problems n n n 3 Figure 15. 1 P. 378 English sentences are incomplete descriptions of the information that are intended to convey. The same expression means different things in different context. No natural language program can be complete because of new words, expression, and meaning can be generated quite freely. There are lots of ways to say the same thing. 344 -471 AI & ES Chapter 6 NLP
NLP Problems 1) Processing written text n n using lexical, syntactic, and semantic knowledge of the language require the real world information 2) Processing spoken language using all information needed above plus additional knowledge about phonology n handle ambiguities in speech n 4 344 -471 AI & ES Chapter 6 NLP
Step in NLP 1) Morphological Analysis 2) Syntactic Analysis 3) Semantic Analysis 4) Discourse Integration 5) Pragmatic Analysis boundaries between these five phrases are often fuzzy. n 5 344 -471 AI & ES Chapter 6 NLP
1. Morphological Analysis n n n Individual words are analyzed into components Nonword tokens such as punctuation are separated from the words I want to print Bill’s. int file extension proper noun possessive suffix 6 344 -471 AI & ES Chapter 6 NLP
2. Syntactic Analysis n n 7 linear sequence of words are transformed into structures show words relate to each other English syntactic analyzer If do not pass the syntactic analyzer reject e. g. (Boy the go to store the) 344 -471 AI & ES Chapter 6 NLP
2. Syntactic Analysis n Example of syntactic analysis Figure 15. 2 p. 382 RM 2, RM 5 n A knowledge base Fragment Figure 15. 3 p. 383 User 073, F 1, Printing, File_Structure, Waiting Mental Event/ Physical Event Animate/Event n Partial meaning for a sentence Figure 15. 4 p. 384 8 344 -471 AI & ES Chapter 6 NLP
Syntax 9 344 -471 AI & ES Chapter 6 NLP
Parse Tree 10 344 -471 AI & ES Chapter 6 NLP
Apply rule 11 344 -471 AI & ES Chapter 6 NLP
3. Semantic Analysis the structures created by the syntactic analyzer are assign meanings n mapping between the syntactic structure and objects in the task domain n If no mapping reject (colorless green ideas sleep furiously) n 1) It must map individual words into appropriate objects in the knowledge base or database. n 2) It must create the correct structures to correspond to the meanings of the individual words combine with each other. n 12 344 -471 AI & ES Chapter 6 NLP
4. Discourse Integration n the meaning of the individual sentence may depend on the sentences that precede it and may influence the meanings of the sentences that follow it. (Ex. John want it. ) “It” depends on the previous sentence. Current user who type word “I” is n n 13 User 068 = Susan_Black We get F 1 with filename in /wsmith/ directory 344 -471 AI & ES Chapter 6 NLP
5. Pragmatic Analysis n n The structure representing what was said is reinterpreted to determine what was actually meant. (Ex. Do you know what time it is? ) we should understand what to do. . Understand to decide what to do as a result n Representing the intended meaning n 14 Figure 15. 5 P. 385 344 -471 AI & ES Chapter 6 NLP
Internal Representative 15 344 -471 AI & ES Chapter 6 NLP
Syntactic Processing n Top-down Parsing n n Bottom-up Parsing n 17 Begin with start symbol and apply the grammar rules forward until the symbols at the terminals of the tree correspond to the components of the sentence being parsed. Begin with the sentence to be parsed and apply the grammar rules backward until a single tree whose terminals are the words of the sentence and whose top node is the start symbol has been produced. 344 -471 AI & ES Chapter 6 NLP
Transition Network 18 344 -471 AI & ES Chapter 6 NLP
ATN : Augmented Transition Network n similar to finite state machine Figure 15. 8 p. 392 An ATN network Figure 15. 9 p. 3923 An ATN Grammar in List Form n sentence “The long file has printed. ” S NP Q 1 AUX NP Det Q 6 Adj (S DCL Q 3 V Q 4 (F) halt Q 6 N Q 7 (F) (NP (FILE (LONG) DEFINITE)) HAS 19 (VP PRINTED)) 344 -471 AI & ES Chapter 6 NLP
Turbo Prolog 32
TURBO PROLOG ftp: //172. 28. 80. 6/older/Dos. Program/TPROLOG Alt + Enter = Big Screen F 1 : Help F 2 : Save F 3 : Load F 6 : Next/Switch F 8 : Previous Goal F 9 : Compile F 10 : Step (For trace) / End Alt + T : Trace ON/OFF Set up window size edit Use arrow key to adjust the size 33 344 -471 AI & ES Chapter 6 NLP
TURBO PROLOG Use the example from the EXAMPLE directory to try to program. Start with EX 03 EX 01. PRO predicates likes(symbol, symbol) clauses likes(ellen, tennis). likes(john, football). likes(tom, baseball). FACTS likes(eric, swimming) likes(mark, tennis). 34 likes(bill, Activity) if likes(mark, Activity) : - likes(tom, Activity). likes(ellen, Activity). 344 -471 AI & ES RULES Chapter 6 NLP
PROLOG. HELP ARITHMETIC Arithmetic operators: +, -, *, /, mod, div Relational operators: >, <, =, >=, <>, >< Functions: sin, cos, tan, arctan, log, exp, sqrt, round, trunc, abs EX: 1 + 2 = 2 + 1, X = 5/2, X = 5 mod 2, 35 344 -471 AI & ES 5 <> 9 Chapter 6 NLP
PREDEFINED DOMAINS char 1 byte characters integer 2 byte integer numbers real 8 byte floating point numbers symbol strings inserted in the internal symbol table string sequences of chars "hello worldn" 36 344 -471 AI & ES Chapter 6 NLP
SUMMARY OF PROGRAM SECTIONS CONSTANTS const 1 = definition const 2 = definition [GLOBAL] DOMAINS dom [, dom] = [reference] declaration 1; declaration 2 listdom = dom* dom = <basisdom> [GLOBAL] DATABASE [ - <databasename> ] [determ] pred 1(. . ) pred 2(. . . ) GLOBAL PREDICATES [determ|nondeterm] pred 1(. . ) -(i, i, o, . . )(i, o, i, . . ) [ language c|pascal|fortran ] [ as "name" ] pred 2(. . . . ) PREDICATES [determ|nondeterm] pred 1(. . ) pred 2(. . . . ) CLAUSES p(. . . . ): -p 1(. . . ), p 2(. . ), . . . . include "filename" 37 Include a file during compilation. 344 -471 AI & ES Chapter 6 NLP
MISCELLANEOUS random(Real. Variable) (real) - (o) random(Max. Value, Random. Int) (integer, integer) - (i, o) sound(Duration, Frequency) (integer, integer) - (i, i) beep date(Year, Month, Day) (integer, integer) - (o, o, o) (i, i, i) time(Hours, Minutes, Seconds, Hundredths) (integer, integer) - (o, o, o, o) (i, i, i, i) trace(on/off) (string) - (i) (o) 38 344 -471 AI & ES Chapter 6 NLP
ERROR & BREAK CONTROL trap (Predicate. Call, Exit. Code, Predicate To. Call. On. Error) exit (Exit. Code) (integer) - (i) if exit to DOS then the DOS errorlevel task processing variable will contain the value given to the exit predicate. break (on/off) (string) - (i) (o) 39 344 -471 AI & ES Chapter 6 NLP
EDITOR 40 display(String) (string) - (i) edit(Input. String, Output. String) (string, string) - (i, o) edit(Input. String, Output. String, Headstr 2, Ms g, Pos, Helpfilename, Edit. Mode, Indent, Insert, Text. Mode, Ret. Pos, Ret. Statu s) (string, string, integer, str ing, integer, integer, int eger) - (i, o, i, i, i, o, o) If the user saves the text from the editor, Head. Str 2 will be used as the file name. editmsg(Input. String, Output. String, Headstr 2, Msg, Pos, Helpfilename, Ret. Status) (string, string, integer, str ing, integer) - (i, o, i, i, i, o) 344 -471 AI & ES Chapter 6 NLP
WINDOW SYSTEM makewindow(Window. No, Scr. Att, Framestr, Ro w, Column, Height, Width) (integer, string, integer, integer) shiftwindow(Window. No) (integer) - (i) (o) gotowindow(Window. No) (integer) - (i) resizewindow(Start. Row, No. Of. Rows, Start. Col, No. Of. Col s) (integer, integer) - (i, i, i, i) colorsetup(Main_Frame) (integer) - (i) 41 344 -471 AI & ES Chapter 6 NLP
INPUT readln(String. Variable) (string) - (o) readint(Intg. Variable) (integer) - (o) readreal(Real. Variable) (real) - (o) readchar(Char. Variable) (char) - (o) keypressed unreadchar(Char. To. Be. Pushed. Back) (Char) - (i) readterm( Domain, Variable ) (Domain. Name, Domain) - (i, _) 42 344 -471 AI & ES Chapter 6 NLP
OUTPUT write( Variable|Constant * ) nl writef( Format. String, Variable|Constant* ) In the format string the following options are known after a percentage sign: %d Normal decimal number. (chars and integers) %u As an unsigned integer. (chars and integers) %R As a database reference number. (database reference numbers) %X As a long hexadecimal number. (strings, database reference numb). %x As a hexadecimal number. (chars and integers). %s Strings. (symbols and strings). %c As a char. (chars and integers). %g Reals in shortest posible format (default for reals) %e Reals in exponetial notation %f Reals in fixed notation %lf Only for C compatibility (fixed reals) 43 n - newline t - tabulator nnn - character with code nnn 344 -471 AI & ES Chapter 6 NLP
The End 44 344 -471 AI & ES Chapter 6 NLP
- Natural language processing nlp - theory lecture
- Natural language processing nlp - theory lecture
- Natural language processing vietnamese
- Probabilistic model natural language processing
- Markov chain natural language processing
- Christopher manning stanford
- Grammar adalah
- Discourse analysis in nlp
- Natural language processing lecture notes
- Language
- Natural language processing fields
- Statistical natural language processing
- Natural language processing games
- Collocation nlp
- Ucla natural language processing
- Prolog language
- Rada mihalcea
- Pengertian bahasa alami
- Natural language processing
- Language synonyms
- Natural language processing
- Dot translation
- Natural language processing lecture notes
- Reference phenomena in nlp
- Kai wei chang
- Nyu natural language processing
- Natural language processing lecture notes
- Natural language processing lecture notes
- Nlp berlin
- Dialogflow prebuilt agents
- Natural language processing
- Bottom up processing example