Presentation is loading. Please wait.

Presentation is loading. Please wait.

1 Inteligenta Artificiala Universitatea Politehnica Bucuresti Anul universitar 2005-2006 Adina Magda Florea

Similar presentations


Presentation on theme: "1 Inteligenta Artificiala Universitatea Politehnica Bucuresti Anul universitar 2005-2006 Adina Magda Florea"— Presentation transcript:

1 1 Inteligenta Artificiala Universitatea Politehnica Bucuresti Anul universitar 2005-2006 Adina Magda Florea http://turing.cs.pub.ro/ia_06

2 2 Curs nr. 13 Prelucrarea limbajului natural 2

3 3 Comunicare n Definite n mesaj, limbaj, protocol n Componentele comunicarii –intentie –generare –sinteza –perceptie –analiza –desambiguare –incorporare

4 4 Acte de comunicare n Teoria actelor de comunicare n locutie n ilocutie n prelocutie –asertive –directive –comisive –permisive –prohibitive –declarative –expresive Tipuri de agenti care comunica

5 5 Definire limbaj n Lexicon n Analiza lexicala n Gramatici n Analiza (pars oratoris) n Terminale, neterminale, reguli de rescriere n simbol de inceput n LHS  RHS n Analza semantica n Analiza pragmatica

6 6 Lexicon Noun  breeze | wumpus | ball Verb  is | see | smell | hit Adjective  right | left | smelly … Adverb  here | there | ahead … Pronoun  me | you | I | it RelPronoun  that | who Name  John | Mary Article  the | a | an Preposition  to | in | on Conjunction  and | or | but

7 7 Gramatica n Neterminale – diferite categorii din propozitie –sentence S –noun phrase NP –verb phrase VP –prepositional phrase PP –relative clause RelClause

8 8 Exemplu S  NP VP | S Conjunction S NP  Pronoun | Noun | Article Noun | NP PP | NP RelClause VP  Verb | VP NP | VP Adjective | VP PP | VP Adverb PP  Preposition NP RelClause  RelPronoun VP

9 9 Analiza sintactica –top-down parsing –bottom-up parsing –in adancime –pe nivel

10 10 Top-Down Parsing "John hit the ball" 1. S 2. S  NP, VP 3. S  Noun, VP 4. S  John, Verb, NP 5. S  John, hit, NP 6. S  John, hit, Article, Noun 7. S  John, hit, the, Noun 8. S  John, hit, the, ball

11 11 Bottom-Up Parsing 1. John, hit, the, ball 2. Noun, hit, the, ball 3. Noun, Verb, the, ball 4. Noun, Verb, Article, ball 5. Noun, Verb, Article, Noun 6. NP, Verb, Article, Noun 7. NP, Verb, NP 8. NP, VP 9. S

12 12 Definite Clause Grammar (DCG) n Gramatici BNF - probleme n Utilizare LP n Gramatici cu clauze definite n DCG – gramatica; propozitie = clauza definita n neterminal = predicat de 1 argument

13 13 In BNF S  NP VP In LP NP(s 1 )  VP(s 2 )  S(Append(s 1, s 2 )) NF Noun  ball | book In LP (s = “ball”  s = “book”)  Noun(s)

14 BNF, DCG, Prolog BNFFOPLPROLOG S  NP VP NP  Noun Noun  stench Noun  wumpus VP  Verb Verb  smells Verb  kills NP(s1)  VP(s2)  S(append(s1,s2)) Noun(s)  NP(s) Verb(s)  VP(s) (s = “stench”  s = “wumpus”)  Noun(s) (v = “smells”  v = “kills”)  Verb(v) sentence([S1, S2]) :- np(S1), vp(S2). np(S):- noun(S). vp(S):- verb(S). noun(stench). noun(wumpus). verb(smells). verb(kills). ?- sentence([wumpus, smells]). ?-sentence([S1, S2]).

15 15 Imbogatire DCG n Imbogatesc neterminale cu argumente suplimentare n Verifica corectitudinea gramaticala n Ataseseaza semantica n Adauga expresii / functii care se testeaza

16 16 Argument pt semantica DCGFOPL PROLOG S(sem)  NP(sem1) VP(sem2) {compose(sem1, sem2, sem)} NP(s1, sem1)  VP(s2, sem2)  S(append(s1, s2)), compose(sem1, sem2, sem) slide urmator semantica compozitionala

17 The dog has legs.(dog parts legs) The ball is yellow.(ball property yellow) The ball is red.(ball property red) The dog bites.(dog action bytes) sentence(S, Sem) :- np(S1, Sem1), vp(S2, Sem2), append(S1, S2, S), Sem = [Sem1 | Sem2]. np([S1, S2], Sem) :- article(S1), noun(S2, Sem). vp([S], Sem) :- verb(S, Sem1), Sem = [action, Sem1]. vp([S1, S2], Sem) :- verb(S1,_), adjective(S2, Sem1), Sem = [property, Sem1]. vp([S1, S2], Sem) :- verb(S1,_), noun(S2, Sem1), Sem = [parts, Sem1]. noun(dog,dog). noun(ball,ball). verb(bytes,bytes). verb(is,is). verb(has,has). adjective(yellow,yellow). adjective(red,red).

18 18 Verificare corectitudine gramaticala n cazuri n subcategorii verbe: compleentul pe care il poate accepta un verb n acord subiect predicat n etc. n Parametrizarea neterminalelor

19 Cazuri Nominativ (subjective) I take the busEu iau autobuzul You take the busTu iei autobuzul He takes the busEl ia autobuzul Acuzativ (objective) He gives me the bookImi da cartea S  NP(Subjective) VP NP(case)  Pronoun (case) | Noun | Article Noun //I VP  VP NP(Objective)//believe him VP  VP PP// turn to the right VP  VP Adjective VP  Verb PP  Preposition NP(Objective) Pronoun(Subjective)  I | you | he | she Pronoun(Objective)  me | you | him | her

20 20 sentence(S) :- np(S1,subjective), vp(S2), append(S1, S2, S). np([S], Case) :- pronoun(S, Case). np([S], _ ) :- noun(S). np([S1, S2], _ ) :- article(S1), noun(S2). pronoun(i, subjective). pronoun(you, _ ). pronoun(he, subjective). pronoun(she, subjective). pronoun(me, objective). pronoun(him, objective). pronoun(her, objective). noun(ball). noun(stick). article(a). article(the).

21 21 Subcategorii verbe n Lista de subcategorii: ce complemente accepta verbul n depinde de verb n S  NP(Subjective) VP(subcat) dar cazuri in care nu depinde n VP(subcat)  VP(subcat) PP n | VP(subcat) Adverb I smell the wumpus now

22 VP(subcat)  {subcat = np} VP(np) NP(Objective) | {subcat = adj} VP(adj) Adjective | {subcat = pp} VP (pp) PP | Verb smell[NP]smell a wumpus [Adjective]smell awfull [PP]smell like a wumpus is[Adjective]is smelly [PP]is in box [NP]is a pit give[NP, PP]give the gold in box to me [NP, NP]give me the gold died[]died

23 S  NP(Subjective) VP(subcat) NP(case)  Pronoun (case) | Noun | Article Noun Pronoun(Subjective)  I | you | he | she Pronoun(Objective)  me | you | him | her VP(subcat)  {subcat = np} VP(np) NP(Objective) | {subcat = adj} VP(adj) Adjective | {subcat = pp} VP (pp) PP | Verb | VP(subcat) PP | VP(subcat) Adverb

24 sentence(S) :- np(S1,subjective), vp(S2), append(S1, S2, S). np([S], Case) :- pronoun(S, Case). np([S], _ ) :- noun(S). np([S1, S2], _ ) :- article(S1), noun(S2). VP(subcat)  VP(subcat) … !!! vp(S, Subcat) :- Subcat = np, vp1(S1, np),np(S2, objective), append(S1, S2, S). vp1([S],np):-verb(S). verb(give). verb(make). vp(S,Subcat) :- vp1(S1, Subcat), pp(S2), append(S1, S2, S).

25 25 Analiza pragmatica n Analiza semantica n Desambiguare n Interpretare pragmatica – utilizare si efect asupra ascultatorului n Indexical - situatia curenta n Anafora – deja mentionate

26 26 Ambiguitate n Lexicala n Sintactica n Referentiala n Pragmatica


Download ppt "1 Inteligenta Artificiala Universitatea Politehnica Bucuresti Anul universitar 2005-2006 Adina Magda Florea"

Similar presentations


Ads by Google