Artificial Intelligence

Transcription

1 CS344: Introduction to Artificial Intelligence Pushpak Bhattacharyya CSE Dept., IIT Bombay Lecture Natural Language Parsing

2 Parsing of Sentences

3 Are sentences flat linear structures? Why tree? Is there a principle in branching When should the constituent give rise to children? What is the hierarchy building principle?

4 Structure Dependency: A Case Study Interrogative Inversion (1) John will solve the problem. Will John solve the problem? Declarative Interrogative (2) a. Susan must leave. Must Susan leave? b. Harry can swim. Can Harry swim? c. Mary has read the book. Has Mary read the book? d. Bill is sleeping. Is Bill sleeping?. The section, Structure dependency a case study here is adopted from a talk given by Howard Lasnik (2003) in Delhi university.

5 Interrogative inversion Structure Independent (1 st attempt) (3)Interrogative inversion process Beginning with a declarative, invert the first and second words to construct an interrogative. Declarative Interrogative (4) a. The woman must leave. *Woman the must leave? b. A sailor can swim. *Sailor a can swim? c. No boy has read the book. *Boy no has read the book? d. My friend is sleeping. *Friend my is sleeping?

6 Interrogative inversion correct pairings Compare the incorrect pairings in (4) with the correct pairings ii in (5): Declarative Interrogative (5) a. The womanmust leave. Must the womanleave? b. A sailor can swim. Can a sailor swim? c. No boy has read the book. Has no boy read the book? d. My friend is sleeping. Is my friend sleeping?

7 Interrogative inversion Structure Independent (2 nd attempt) p) (6) Interrogative inversion process: Beginning i with a declarative, move the auxiliary verb to the front to construct an interrogative. Declarative Interrogative (7) a. Bill could be sleeping. *Be Bill could sleeping? Could Bill be sleeping? b. Mary has been reading. *Been Mary has reading? Has Mary been reading? c. Susan should have left. *Have Susan should left? Should Susan have left?

8 Structure independent (3 rd attempt): (8) Interrogative inversion process Beginning i with a declarative, move the first auxiliary verb to the front to construct an interrogative. Declarative Interrogative (9) a. The manwho is here can swim. *Is the manwho here can swim? b. The boy who will play has left. *Will the boy who play has left?

9 Structure Dependent Correct Pairings For the above examples, fronting the second auxiliary verb gives the correct form: Declarative Interrogative (10) a.the man who is here can swim. Can the man who is here swim? b.the boy who will play has left. Has the boy who will play left?

10 Natural transformations are structure dependent (11) Does the child acquiring English learn these properties? (12) We are not dealing with a peculiarity of English. No known human language g has a transformational process that would produce pairings like those in (4), (7) and (9), repeated below: (4) a. The woman must leave. *Woman the must leave? (7) a. Bill could be sleeping. *Be Bill could sleeping? (9) a. The man who is here can swim. *Is the man who here can swim?

11 Deeper trees needed for capturing sentence structure NP This wont do! Flat structure! The AP book with the blue cover big of poems [The big book of poems with the [The big book of poems with the Blue cover] is on the table.

12 Other languages NP English The AP book with the blue cover big NP of poems AP Hindi kitaab niil jilda vaalii kavita kii badii [niil jilda vaalii kavita kii kitaab]

13 Other languages: contd NP English The AP book with the blue cover big NP of poems AP Bengali niil malaat deovaa kavitar motaa ti bai [niil malaat deovaa kavitar bai ti]

14 s are at the same level: flat with respect to the head word book NP No distinction in terms of dominance or c-command command The AP book with the blue cover big of poems [The big book of poems with the [The big book of poems with the Blue cover] is on the table.

15 Constituency test of Replacement runs into problems One-replacement: I bought the big [book of poems with the blue cover] not the small [one] One-replacemen targets book of poems with the blue cover Another one-replacement: I bought the big [book of poems] with the blue cover not the small [one] with the red cover One-replacemen targets book of poems

16 More deeply embedded structure NP N 1 The AP N 2 big N 3 N book with the blue cover of poems

17 To target N 1 I want [ NP this [ N big book of poems with the red cover] and not [ N that [ N one]]

18 Bar-level projections Add intermediate structures NP (D) N N (AP) N N () N () () indicates optionality

19 New rules produce this tree NP N-bar N 1 The AP N 2 big N 3 N book with the blue cover of poems

20 As opposed to this tree NP The AP book with the blue cover big of poems

21 V-bar What is the element in verbs corresponding to one-replacement for nouns do-so or did-so

22 As opposed to this tree NP The AP book with the blue cover big of poems

23 I [eat beans with a fork] VP eat NP with a fork beans No constituent that groups together V and NP and excludes No constituent that groups together V and NP and excludes

24 Need for intermediate constituents I [eat beans] with VP a fork but Ram [does so] with a spoon V 1 VP V V V () V V (NP) V 2 V NP with a fork eat beans

25 How to target V 1 I [eat beans with VPa fork], and Ram [does so] too. V 1 VP V V V () V V (NP) V 2 V NP with a fork eat beans

26 Parsing Algorithms

27 A simplified grammar S NP VP NP DT N N VP V ADV V

28 A segment of English Grammar S (C) S S {NP/S } VP VP (AP+) (VAUX) V (AP+) ({NP/S }) (AP+) (+) (AP+) NP (D) (AP+) N (+) P NP AP (AP) A

29 Example Sentence People e laugh These are positions Lexicon: People - N, V Laugh - N, V This indicate that both Noun and Verb is possible for the word People

30 Top-Down Parsing State Backup State Action ((S) 1) - - Position of input pointer 2. ((NP VP)1) - - 3a. ((DT N VP)1) ((N VP) 1) - 3b. ((N VP)1) ((VP)2) - Consume People 5a. ((V ADV)2) ((V)2) - 6. ((ADV)3) ((V)2) Consume laugh 5b. ((V)2) ((.)3) - Consume laugh Termination Condition : All inputs over. No symbols remaining. Note: Input symbols can be pushed back.

31 Discussion for Top-Down Parsing This kind of searching is goal driven This kind of searching is goal driven. Gives importance to textual precedence (rule precedence). No regard for data, a priori (useless expansions made).

32 Bottom-Up Parsing Some conventions: N 12 Represents positions S 1? -> NP 12 VP 2? End position unknown Work on the LHS done, while the work on RHS remaining

33 Bottom-Up Parsing (pictorial representation) S -> NP 12 VP 23 People Laugh N 12 N V 12 V 23 NP 12 -> N 12 NP 23 -> N 23 VP 12 -> V 12 VP 23 -> V S 1? -> NP 12 VP 2?

34 Problem with Top-Down Parsing Left Recursion Suppose you have A-> AB rule. Then we will have the expansion as follows: ((A)K) -> ((AB)K) -> ((ABB)K)..

35 Combining i top-down and bottom-up strategies

36 Top-Down Bottom-Up Chart Parsing Combines advantages of top-down & bottomup pparsing. Does not work in case of left recursion. e.g. People laugh People noun, verb Laugh noun, verb Grammar S NP VP NP DT N N VP V ADV V

37 Transitive Closure People laugh S NP VP NP N VP V NP DT N S NP VP S NP VP NP N N VP V V ADV success VP V

38 Arcs in Parsing Each arc represents a chart which records Completed work (left of ) Expected work (right of )

39 Example People laugh loudly S NP VP NP N VP V VP V ADV NP DT N S NP VP VP V ADV S NP VP NP N VP V ADV S NP VP VP V

40 Dealing With Structural Ambiguity Multiple parses for a sentence The man saw the boy with a telescope. The man saw the mountain with a telescope. The man saw the boy with the ponytail. At the level of syntax, all these sentences are ambiguous. But semantics can disambiguate 2 nd &3 rd sentence.

41 Prepositional Phrase () Attachment Problem V NP 1 P NP 2 (Here P means preposition) NP 2 attaches to NP 1? or NP 2 attaches to V?

42 Parse Trees for a Structurally Ambiguous Sentence Let the grammar be S NP VP NP DT N DT N PNP VP V NP V NP For the sentence, I saw a boy with a telescope

43 Parse Tree - 1 S NP VP N V NP I saw Det N a boy P NP with Det N a telescope

44 Parse Tree -2 S NP VP N V NP I saw Det N a boy P with NP Det N a telescope