1. 1 Natural Language Processing Chapter 6

2. 344-471 AI & ESChapter 6 NLP 2 NLP Language translation / multilingual translation Language understanding Figure 14.5 p. 365 Interaction among component Figure 14.6 p. 366 A speech Waveform

3. 344-471 AI & ESChapter 6 NLP 3 NLP Problems 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.

4. 344-471 AI & ESChapter 6 NLP 4 NLP Problems 1) Processing written text 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 handle ambiguities in speech

5. 344-471 AI & ESChapter 6 NLP 5 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.

6. 344-471 AI & ESChapter 6 NLP 6 1. Morphological Analysis Individual words are analyzed into components Nonword tokens such as punctuation are separated from the words I want to print Bill ’ s.int file. proper noun possessive suffix file extension

7. 344-471 AI & ESChapter 6 NLP 7 2. Syntactic Analysis linear sequence of words are transformed into structures show how words relate to each other English syntactic analyzer If do not pass the syntactic analyzer  reject e.g. (Boy the go to store the)

8. 344-471 AI & ESChapter 6 NLP 8 Example of syntactic analysis Figure 15.2 p. 382  RM2, RM5, RM5 A knowledge base Fragment Figure 15.3 p. 383 User073, F1, Printing, File_Structure, Waiting Mental Event/ Physical Event Animate/Event Partial meaning for a sentence Figure 15.4 p. 384 2. Syntactic Analysis

9. 344-471 AI & ESChapter 6 NLP 9 Syntax

10. 344-471 AI & ESChapter 6 NLP 10 Parse Tree

11. 344-471 AI & ESChapter 6 NLP 11 Apply rule

12. 344-471 AI & ESChapter 6 NLP 12 3. Semantic Analysis the structures created by the syntactic analyzer are assign meanings mapping between the syntactic structure and objects in the task domain If no mapping  reject (colorless green ideas sleep furiously) 1) It must map individual words into appropriate objects in the knowledge base or database. 2) It must create the correct structures to correspond to the meanings of the individual words combine with each other.

13. 344-471 AI & ESChapter 6 NLP 13 4. Discourse Integration 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 User068 = Susan_Black We get F1 with filename in /wsmith/ directory

14. 344-471 AI & ESChapter 6 NLP 14 5. Pragmatic Analysis 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 Representing the intended meaning Figure 15.5 P. 385

15. 344-471 AI & ESChapter 6 NLP 15 Internal Representative

16. 344-471 AI & ESChapter 6 NLP 16 Syntactic Processing (2) Grammar  declarative representation  syntactic facts about the language Figure 15.6 p.387 Parser  procedure  compares the grammar against input sentences to produce parsed structure. Figure 15.7 p.388 A parse tree for a sentence

17. 344-471 AI & ESChapter 6 NLP 17 Top-down Parsing 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. Bottom-up Parsing 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. Syntactic Processing

18. 344-471 AI & ESChapter 6 NLP 18 Transition Network

19. 344-471 AI & ESChapter 6 NLP 19 ATN : Augmented Transition Network similar to finite state machine Figure 15.8 p.392 An ATN network Figure 15.9 p.3923An ATN Grammar in List Form sentence  “ The long file has printed. ” S  NP  Q1  AUX  Q3  V  Q4 (F) halt NP  Det  Q6  Adj  Q6  N  Q7 (F) (S DCL (NP (FILE (LONG) DEFINITE)) HAS (VP PRINTED))

20. 344-471 AI & ESChapter 6 NLP 20 Unification Grammar DAGs : Direct Acyclic Graph the graph corresponding to “ the ” and “ file ” are [CAT: DET[CAT: N [NP [DET: N LEX:the]LEX : file HEAD: file NUMBER: SING] NUMBER: SING]]

21. 344-471 AI & ESChapter 6 NLP 21 Semantic Processing (3) Step 1. Lexicon  look up the individual words in a dictionary and extract their meaning. Step 2 Lexicon disambiguity or Word sense disambiguity words may have more than one meaning e.g. bank ( ธนาคาร หรือ ตลิ่ง ), diamond p.398 ( เพชร หรือ รูปเหลี่ยม ) use semantic marker  PHYSICAL OBJECT, ANIMATE OBJECT, ABSTRACT OBJECT e.g. I drop my diamond...

22. 344-471 AI & ESChapter 6 NLP 22 Semantic Processing (3) use semantic marker PHYSICAL OBJECT ANIMATE OBJECT ABSTRACT OBJECT e.g. I drop my diamond... note that “ My lawn hates the cold ” is a correct semantic as well, although lawn can not act the verb hate..... but this sentence can be use in the good English sense.

23. 344-471 AI & ESChapter 6 NLP 23 Sentence Level Processing (3) 1) Semantic grammars 2) Case grammars 3) Conceptual parsing 4) Approximately compositional semantic interpretation

24. 344-471 AI & ESChapter 6 NLP 24 1) Semantic grammars - semantic action associate with the grammar rule - Figure 15.10 p. 401 e.g. “ I want to ”  ACTION - Figure 15.11 p. 402 Parsing Result with semantic grammars Sentence Level Processing (3)

25. 344-471 AI & ESChapter 6 NLP 25 2) Case grammars : passing process driven from the sentence ’ s main verb. - Figure 15.12 p. 404 Active and passive sentence : Susan printed a file. = The file was printed by Susan. - Figure 15.13 p. 404 Similar sentence : Mother baked for three hours. = The pie baked for three hours. - Word case p. 405 : (A) Agent, (I) Instrument, (F) Factitive, (L) Locatives, (S) Source, (G) Goal, (B) Beneficiary, (T) Time, (O) Object Sentence Level Processing (3)

26. 344-471 AI & ESChapter 6 NLP 26 2) Case grammars - Figure 15.14 p. 406 Some verb case frames : open [_ _ O (I) (A)] A : Instigator of the action D : Entity effect by the action : die [_ _ D] John die. : kill [_ _ D (I) (A)] Bill killed John. Bill killed John with a knife. : want [_ _A O] John wanted some ice cream. John wanted Marry to go to store. Sentence Level Processing (3)

27. 344-471 AI & ESChapter 6 NLP 27 3) Conceptual parsing strategy for finding both the structure and the meaning of the sentence in one step. use verb-ACT dictionary Figure 15.15 p. 407 e.g. “want” 1) stative (wanting something to happen) 2) transitive ATRANS (wanting an object) 3) intransitive PTRANS (wanting a person) Sentence Level Processing (3)

28. 344-471 AI & ESChapter 6 NLP 28 3) Conceptual parsing CD : Conceptual Dependency structure : passing process driven from the sentence’s main verb with more details in the lower level. Figure 15.16 p. 407 “John wanted Mary to go to the store.” (PTRANS) Sentence Level Processing (3)

29. 344-471 AI & ESChapter 6 NLP 29 4) Approximately compositional semantic interpretation - Semantic interpretation rules Figure 15.18 p. 411 - Combining Mapping Knowledge Figure 15.19 p. 412 wanting : agent : (animate), object : (state or event) Sentence Level Processing (3)

30. 344-471 AI & ESChapter 6 NLP 30 Discourse (4) and Pragmatic Processing (5) use to understand a single sentence. p. 415 – 416 Relationship between discourse contexts Names of individuals Dave went to the movie. Parts of actions. 1) John went on a business trip to New York. 2) He left on an early morning flight. Causal chains.... Planning sequences....

31. 344-471 AI & ESChapter 6 NLP 31 knowledge to focus the current focus on dialogue a model of each participant’s current beliefs the rule of conversation shared by all participants Modeling Individual beliefs p.419 Model logic : Three belief spaces Figure 15.20 p.420 temporal logics allow to talk about the truth of the set of proposition at current state of the real world, in the past, and in the future as well. conditional logic allow to talk about the truth or falsehood under some circumstances Discourse (4) and Pragmatic Processing (5)

32. 32 Turbo Prolog

33. 344-471 AI & ESChapter 6 NLP 33 ftp://172.28.80.6/older/DosProgram/TPROLOG Alt + Enter = Big Screen F1 : Help F2 : Save F3 : Load F6 : Next/Switch F8 : Previous Goal F9 : Compile F10 : Step (For trace) / End Alt + T : Trace ON/OFF Set up  window size  edit Use arrow key to adjust the size TURBO PROLOG

34. 344-471 AI & ESChapter 6 NLP 34 Use the example from the EXAMPLE directory to try to program. Start with EX03EX01.PRO predicates likes(symbol,symbol) clauses likes(ellen, tennis). likes(john, football). likes(tom, baseball). likes(eric, swimming) likes(mark, tennis). likes(bill, Activity) if likes(tom, Activity). likes(mark, Activity) :- likes(ellen, Activity). TURBO PROLOG FACTS RULES

35. 344-471 AI & ESChapter 6 NLP 35 ARITHMETIC Arithmetic operators: +, -, *, /, mod, div Relational operators: >, =,, >< Functions: sin, cos, tan, arctan, ln, log, exp, sqrt, round, trunc, abs EX: 1 + 2 = 2 + 1, X = 5/2, X = 5 mod 2, 5 <> 9 PROLOG.HELP

36. 344-471 AI & ESChapter 6 NLP 36 char1 byte characters integer2 byte integer numbers real8 byte floating point numbers symbolstrings inserted in the internal symbol table stringsequences of chars "hello world\n" PREDEFINED DOMAINS

37. 344-471 AI & ESChapter 6 NLP 37 CONSTANTS const1 = definition const2 = definition [GLOBAL] DOMAINS dom [,dom] = [reference] declaration1; declaration2 listdom = dom* dom = [GLOBAL] DATABASE [ - ] [determ] pred1(....) pred2(.....) GLOBAL PREDICATES [determ|nondeterm] pred1(.........) -(i,i,o,..)(i,o,i,..) [ language c|pascal|fortran ] [ as "name" ] pred2(........) PREDICATES [determ|nondeterm] pred1(.........) pred2(........) CLAUSES p(....):-p1(...), p2(.....),.... include "filename" Include a file during compilation. SUMMARY OF PROGRAM SECTIONS

38. 344-471 AI & ESChapter 6 NLP 38 random(RealVariable) (real) - (o) random(MaxValue,RandomInt) (integer,integer) - (i,o) sound(Duration,Frequency) (integer,integer) - (i,i) beep date(Year,Month,Day) (integer,integer,integer) - (o,o,o) (i,i,i) time(Hours,Minutes,Seconds,Hundredths) (integer,integer,integer,integer) - (o,o,o,o) (i,i,i,i) trace(on/off) (string) - (i) (o) MISCELLANEOUS

39. 344-471 AI & ESChapter 6 NLP 39 trap (PredicateCall,ExitCode,Predicate ToCallOnError) exit exit (ExitCode) (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) ERROR & BREAK CONTROL

40. 344-471 AI & ESChapter 6 NLP 40 display(String) (string) - (i) edit(InputString,OutputString) (string,string) - (i,o) edit(InputString,OutputString,Headstr,Headstr2,Ms g,Pos,Helpfilename, EditMode,Indent,Insert,TextMode,RetPos,RetStatu s) (string,string,string,string,string,integer,str ing,integer,integer,integer,integer,integer,int eger) - (i,o,i,i,i,i,i,i,i,i,i,o,o) If the user saves the text from the editor, HeadStr2 will be used as the file name. editmsg(InputString,OutputString,Headstr,Headstr2,Msg,Pos,Helpfilename,RetStatus) (string,string,string,string,string,integer,str ing,integer)- (i,o,i,i,i,i,i,o) EDITOR

41. 344-471 AI & ESChapter 6 NLP 41 makewindow(WindowNo,ScrAtt,FrameAtt,Framestr,Ro w,Column,Height,Width) (integer,integer,integer,string,integer,integ er,integer,integer) shiftwindow(WindowNo) (integer) - (i) (o) gotowindow(WindowNo) (integer) - (i) resizewindow(StartRow,NoOfRows,StartCol,NoOfCol s) (integer,integer,integer,integer) - (i,i,i,i) colorsetup(Main_Frame) (integer) - (i) WINDOW SYSTEM

42. 344-471 AI & ESChapter 6 NLP 42 readln(StringVariable) (string) - (o) readint(IntgVariable) (integer) - (o) readreal(RealVariable) (real) - (o) readchar(CharVariable) (char) - (o) keypressed unreadchar(CharToBePushedBack) (Char) - (i) readterm( Domain, Variable ) (DomainName,Domain) - (i,_) INPUT

43. 344-471 AI & ESChapter 6 NLP 43 write( Variable|Constant * ) nl writef( FormatString, 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) \n - newline \t - tabulator \nnn - character with code nnn OUTPUT

44. 344-471 AI & ESChapter 6 NLP 44 The End