# 1 inteligenta artificiala universitatea politehnica bucuresti anul universitar 2003-2004 adina magda...

of 55 /55
1 Inteligenta Inteligenta Artificiala Artificiala Universitatea Politehnica Bucuresti Anul universitar 2003-2004 Adina Magda Florea http://turing.cs.pub.ro/ ia_2005

Author: britney-white

Post on 27-Dec-2015

228 views

Category:

## Documents

Embed Size (px)

TRANSCRIPT

1

Inteligenta ArtificialaInteligenta Artificiala

Universitatea Politehnica BucurestiAnul universitar 2003-2004

http://turing.cs.pub.ro/ia_2005

2

Curs nr. 12

Prelucrarea limbajului natural

(Natural Language Processing)

2

3

Defining Languages with Defining Languages with Backus-Naur Form (BNF)Backus-Naur Form (BNF)

A formal language is defined as a set of strings, where each string is a sequence of symbols

All the languages consist of an infinite set of strings need a concise way to characterize the set use a grammar

Terminal Symbols – Symbols or words that make up the strings of the languageExample– Set of symbols for the language of simple arithmetic

expressions– {0,1,2,3,4,5,6,7,8,9,+,-,*,/,(,)}

4

Components in a BNF Grammar Components in a BNF Grammar

Nonterminal Symbols– Categorize subphrases of the language

Example– The nonterminal symbol NP (NounPhrase)

denotes an infinite set of strings, including “you” and “the big dog”

5

Components in a BNF GrammarComponents in a BNF Grammar

Start Symbol– Nonterminal symbol that denotes the complete

strings of the language

Set of rewrite rules or productions– LHS RHS– LHS is a nonterminal– RHS is a sequence of zero or more symbols

(either terminal or nonterminal)

6

Example: BNF Grammar for Simple Arithmetic Expressions

Exp Exp Operator Exp | (Exp) | Number

Number Digit | Number Digit

Digit 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9Operator + | - | * | /

7

The Component Steps of The Component Steps of CommunicationCommunication

A typical communication, in which the speaker S wants to transmit the proposition P to the hearer H using words W, is composed of 7 processes.

3 take place in the speaker

4 take place in the hearer

8

Processes in the SpeakerProcesses in the Speaker

Intention– S wants H to believe P (where S typically

believes P) Generation

– S chooses the words W (because they express the meaning P)

Synthesis – S tells the words W (usually addressing them to

H)

9

Processes in the HearerProcesses in the Hearer

Perception– H perceives W’ (ideally W’ = W, but

misperception is possible)

Analysis – H infers that W’ has possible meanings P1,

…,Pn (words and phrases can have several meanings)

10

Processes in the Hearer Processes in the Hearer

Disambiguation– H infers that S intended to express Pi

(where ideally Pi = P, but misinterpretation is possible)

Incorporation– H decides to believe Pi (or rejects it if it is

out of line with what H already believes)

11

ObservationsObservations

If the perception refers to spoken expressions, this is speech recognition

If the perception refers to hand written expressions, this is recognition of hand writing

Neural networks have been successfully used to both speech recognition and to hand writing recognition

12

Observations Observations

The analysis, disambiguation and incorporation form natural language understanding are relying on the assumption that the words of the sentence are known

Many times, recognition of individual words may be driven by the sentence structure, so perception and analysis interact, as well as analysis, disambiguation, and incorporation

13

Defining a GrammarDefining a Grammar

Lexicon - list of allowable vocabulary words, grouped in categories (parts of speech):– open classes - words are added to the

category all the time (natural language is dynamic, it constantly evolves)

– closed classes - small number of words, generally it is not expected that other words will be added

14

Example - A Small Lexicon

Noun stench | breeze | wumpus ..Verb is | see | smell ..Adjective right | left | smelly …Adverb here | there | ahead …Pronoun me | you | I | itRelPronoun that | whoName John | Mary Article the | a | an Preposition to | in | on Conjunction and | or | but

15

The Grammar Associated to the The Grammar Associated to the LexiconLexicon

Combine the words into phrases Use nonterminal symbols to define

different kinds of phrases– sentence S– noun phrase NP– verb phrase VP– prepositional phrase PP– relative clause RelClause

16

Example - The Grammar Associated to the Lexicon

S NP VP | S Conjunction SNP Pronoun | Noun | Article Noun |

NP PP | NP RelClauseVP Verb | VP NP | VP Adjective |

VP PP | VP AdverbPP Preposition NPRelClause RelPronoun VP

17

Syntactic Analysis (Parsing)Syntactic Analysis (Parsing)

Parsing is the problem of constructing a derivation tree for an input string from a formal definition of a grammar.

Parsing algorithms may be divided into two classes:– top-down parsing– bottom-up parsing

18

Top-Down ParsingTop-Down Parsing

Start with the top-level sentence symbol and attempt to build a tree whose leaves match the target sentence's words (the terminals)

Better if many alternative terminal symbols for each word

Worse if many alternative rules for a phrase

19

Example for 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

20

Bottom-Up ParsingBottom-Up Parsing

Start with the words in the sentence (the terminals) and attempt to find a series of reductions that yield the sentence symbol

Better if many alternative rules for a phrase

Worse if many alternative terminal symbols for each word

21

Example for 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

22

Definite Clause Grammar (DCG)Definite Clause Grammar (DCG)

Problems with BNF Grammar– BNF only talks about strings, not meanings– Want to describe context-sensitive

grammars, but BNF is context-free Introduce a formalism that can handle

both of these problems Use the first-order logic to talk about

strings and their meanings

23

Definite Clause Grammar (DCG)Definite Clause Grammar (DCG)

We are interested in using language for communication need some way of associating a meaning with each string

Each nonterminal symbol becomes a one-place predicate that is true of strings that are phrases of that category

Example– Noun(“ball”) is a true logical sentence– Noun(“the”) is a false logical sentence

24

Definite Clause Grammar (DCG)Definite Clause Grammar (DCG)

A definite clause grammar (DCG) is a grammar in which every sentence must be a definite clause.

A definite clause is a type of Horn clause that, when written as an implication, has exactly one atom in the conclusion and a conjunction of zero or more atoms in the hypothesis, for example A1 A2 … C1

25

Example 1

In BNF notation, we have: S NP VP

In First-Order Logic notation, we have:NP(s1) VP(s2) S(Append(s1, s2))

We read: If there is a string s1 that is a noun phrase and a string s2 that is a verb phrase, then the string formed by appending them together is a sentence

26

Example 2

In BNF notation, we have: Noun ball | book

In First-Order Logic notation, we have:(s = “ball” s = “book”) Noun(s)

We read: If s is the string “ball” or the string “book”, then the string s is a noun

27

Rules to Translate BNF in DCGRules to Translate BNF in DCG

BNF DCG

X Y Z Y(s1) Z(s2) X(Append(s1,s2))

X word X(["word"])

X Y | Z Y(s) X(s) Z(s) X(s)

28

Augmenting the DCGAugmenting the DCG

Extend the notation to incorporate grammars that can not be expressed in BNF

Nonterminal symbols can be augmented with extra arguments

29

Augmenting the DCG Augmenting the DCG Add one argument for semanticsAdd one argument for semantics

In DCG, the nonterminal NP translates as a one-place predicate where the single argument is a string: NP(s)

In the augmented DCG, we can write NP(sem) to express “an NP with semantics sem”. This gets translated into logic as the two-place predicate NP(sem, s)

30

Augmenting the DCG Augmenting the DCG Add one argument for semanticsAdd one argument for semantics

DCG FOPL 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)

See later on

31

Semantic InterpretationSemantic Interpretation

Compositional semantics - the semantics of any phrase is a function of the semantics of its subphrases; it does not depend on any other phrase before, after, or encompassing the given phrase

But natural languages does not have a compositional semantics for the general case.

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 = [property, Sem1].

vp([S1, S2], Sem) :- verb(S1), adjective(S2, color, Sem1),Sem = [color, Sem1].

vp([S1, S2], Sem) :- verb(S1), noun(S2, Sem1), Sem = [parts, Sem1].

33

Problems with Augmented DCGProblems with Augmented DCG

The previous grammar will generate sentences that are not grammatically correct

NL is not a context free language Must deal with

– cases– agreement between subject and main verb in the

sentence (predicate)– verb subcategorization: the complements that a

verb can accept

34

SolutionSolution

Augment the existing rules of the grammar to deal with context issues

Start by parameterizing the categories NP and Pronoun so that they take a parameter indicating their case

CASESNominative case (subjective case) + agreementI take the bus Je prends l’autobus Eu iau autobuzulYou take the bus Tu prends l’autobus Tu iei autobuzulHe takes the bus Il prend l’autobus El ia autobuzul Accusative case (objective case)He gives me the book Il me donne le livre El imi da cartea

Dative case

You are talking to me Il parle avec moi El vorbeste cu mine

36

Example - The Grammar Using Augmentations to Represent Noun Cases

S NP(Subjective) VPNP(case) Pronoun (case) | Noun | Article NounPronoun(Subjective) I | you | he | shePronoun(Objective) me | you | him | her

37

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).

38

Verb SubcategorizationVerb Subcategorization

Augment the DCG with a new parameter to describe the verb subcategorization

The grammar must state which verbs can be followed by which other categories. This is the subcategorization information for the verb

Each verb has a list of complements

39

Integrate Verb Subcategorization Integrate Verb Subcategorization into the Grammarinto the Grammar

A subcategorization list is a list of complement categories that the verb accepts

Augment the category VP to take a subcategorization argument that indicates the complements that are needed to form a complete VP

40

Integrate Verb Subcategorization Integrate Verb Subcategorization into the Grammarinto the Grammar

Change the rule for S to say that it requires a verb phrase that has all its complements, and thus a subcategorization list of [ ]

Rule S NP(Subjective) VP([ ])– The rule can be read as “A sentence can

be composed of a NP in the subjective case, followed by a VP which has a null subcategorization list “

41

Integrate Verb Subcategorization Integrate Verb Subcategorization into the Grammarinto the Grammar

– Verb phrases can take adjuncts, which are phrases that are not licensed by the individual verb, but rather may appear in any verb phrase

– Phrases representing time and place are adjuncts, because almost any action or event can have a time or a place

I smell the wumpus now–

42

VP(subcat) VP([NP | subcat]) NP(Objective)| VP([Adjective | subcat]) Adjective| VP ([PP | subcat]) PP| Verb(subcat)| VP(subcat) PP| VP(subcat) Adverb

The first line can be read as “A VP, with a given subcategorization list, subcat, can be formed by a VP followed by a NP in the objective case, as long as that VP has a subcategorization list that starts with the symbol NP and is followed by the elements of the list subcat ”

43

give [NP, PP] give the gold in box to me[NP, NP] give me the gold

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

died [] died

believe [S] believe the wumpus is dead

VP(subcat) VP([NP | subcat]) NP(Objective)| VP([Adjective | subcat]) Adjective| VP ([PP | subcat]) PP| Verb(subcat)| VP(subcat) PP| VP(subcat) Adverb

vp(S, [np | Subcat]) :- vp(S1, [np | Subcat]), np(S2, objective),

append(S1, S2, S).

vp(give, [np, pp]).vp(give, [np, np]). vp(smell, [np]).vp(smell,[adjective]).vp(smell,[pp]).

But dangerous to translateVP(subcat) VP(subcat) PP

Solutionvp(S, Subcat) :- vp1(S1, Subcat), pp(S2), append(S1, S2, S).

46

Generative Capacity of Generative Capacity of Augmented GrammarsAugmented Grammars

The generative capacity of augmented grammars depends on the number of values for the augmentations

If there is a finite number, then the augmented grammar is equivalent to a context-free grammar

47

Semantic InterpretationSemantic Interpretation

The semantic interpretation is responsible for getting all possible interpretations, and disambiguation is responsible for choosing the best one.

Disambiguation is done starting from the pragmatic interpretation of the sentence.

48

Pragmatic InterpretationPragmatic Interpretation

Pragmatics shows how the language is used and its effects on the listener

Pragmatics will tell why it is not appropriate to answer "Yes" to the question "Do you know what time it is?"

49

IndexicalsIndexicals

Indexical - phrase that refer directly to the current situation

Example– I am in Bucharest today.

50

AnaphoraAnaphora

Anaphora - the occurrence of phrases referring to objects that have been mentioned previously

Example

– John was hungry. He entered a restaurant.

– The ball hit the house. It broke the window.

51

AmbiguityAmbiguity

Lexical Ambiguity Syntactic Ambiguity Referential Ambiguity Pragmatic Ambiguity

52

Lexical AmbiguityLexical Ambiguity

A word has more than one meaning Examples

– A clear sky– A clear profit– The way is clear– John is clear– It is clear that ...

53

Syntactic AmbiguitySyntactic Ambiguity

Can occur with or without lexical ambiguity

Examples– I saw the Statue of Liberty flying over New

York.– I saw John in a restaurant with a telescope.

54

Referential AmbiguityReferential Ambiguity

Occurs because natural languages consist almost entirely of words for categories, not for individual objects

Example– John met Mary and Tom. They went to a

restaurant.– Block A is on block B and it is not clear.

55

Pragmatic AmbiguityPragmatic Ambiguity

Occurs when the speaker and the hearer disagree on what the current situation is

Example– I will meet you tomorrow.