CS626-449: Speech, Natural Language Processing and the Web/Topics in Artificial Intelligence - PowerPoint PPT Presentation

Loading...

PPT – CS626-449: Speech, Natural Language Processing and the Web/Topics in Artificial Intelligence PowerPoint presentation | free to download - id: 1fadc4-ZDc1Z



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

CS626-449: Speech, Natural Language Processing and the Web/Topics in Artificial Intelligence

Description:

CS626-449: Speech, Natural Language Processing and the Web/Topics in Artificial Intelligence ... [The big book of poems with the. Blue cover] is on the table. ... – PowerPoint PPT presentation

Number of Views:55
Avg rating:3.0/5.0
Slides: 31
Provided by: cseIi8
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: CS626-449: Speech, Natural Language Processing and the Web/Topics in Artificial Intelligence


1
CS626-449 Speech, Natural Language Processing
and the Web/Topics in Artificial Intelligence
  • Pushpak Bhattacharyya
  • CSE Dept., IIT Bombay
  • Lecture 12 Deeper Verb Structure Different
    Parsing Algorithms

2
Types of Languages-
  • Head Initial
  • Indian Languages
  • Japanese (with a bit of exception)
  • Head Final
  • English

3
Head Initial Head Final
HEAD INITIAL HEAD FINAL
NP eats rice ???? ?? ??? ??
VP president of India ???? ?? ??????????
PP of India ???? ??
ADJP very intelligent ???? ?????????
4
Deeper trees needed for capturing sentence
structure
This wont do! Flat structure!
NP
PP
PP
AP
The
with the blue cover
book
of poems
big
The big book of poems with the Blue cover is on
the table.
5
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-replacement 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-replacement targets book of poems

6
More deeply embedded structure
NP
N1
The
AP
N2
N3
big
PP
with the blue cover
N book
PP
of poems
7
To target N1
  • I want NPthis Nbig book of poems with the red
    cover and not Nthat None

8
V-bar
  • What is the element in verbs corresponding to
    one-replacement for nouns
  • do-so or did-so

9
I eat beans with a fork
VP
PP
eat
NP
with a fork
beans
No constituent that groups together V and NP and
excludes PP
10
Need for intermediate constituents
  • I eat beans with a fork but Ram does so with
    a spoon

VP
V1
VP?V V? V (PP) V? V (NP)
V2
PP
V
NP
with a fork
eat
beans
11
How to target V1
  • I eat beans with a fork, and Ram does so too.

VP
V1
VP?V V? V (PP) V? V (NP)
V2
PP
V
NP
with a fork
eat
beans
12
Parsing Algorithm
13
A simplified grammar
  • S ? NP VP
  • NP ? DT N N
  • VP ? V ADV V

14
A segment of English Grammar
  • S?(C) S
  • S?NP/S VP
  • VP?(AP) (VAUX) V (AP) (NP/S) (AP) (PP)
    (AP)
  • NP?(D) (AP) N (PP)
  • PP?P NP
  • AP?(AP) A

15
Example Sentence
  • People laugh
  • 2 3
  • Lexicon
  • People - N, V
  • Laugh - N, V

These are positions
This indicate that both Noun and Verb is possible
for the word People
16
Top-Down Parsing
  • State
    Backup State
    Action
  • --------------------------------------------------
    --------------------------------------------------
    -
  • 1. ((S) 1)
    -
    -
  • 2. ((NP VP)1)
    -
    -
  • 3a. ((DT N VP)1)
    ((N VP) 1) -
  • 3b. ((N VP)1)
    -
    -
  • 4. ((VP)2)
    -
    Consume People
  • 5a. ((V ADV)2)
    ((V)2)
    -
  • 6. ((ADV)3)
    ((V)2) Consume
    laugh
  • 5b. ((V)2)
    -
    -
  • 6. ((.)3)
    -
    Consume laugh
  • Termination Condition All inputs over. No
    symbols remaining.
  • Note Input symbols can be pushed back.

Position of input pointer
17
Discussion for Top-Down Parsing
  • This kind of searching is goal driven.
  • Gives importance to textual precedence (rule
    precedence).
  • No regard for data, a priori (useless expansions
    made).

18
Bottom-Up Parsing
  • Some conventions
  • N12
  • S1? -gt NP12 VP2?

Represents positions
Work on the LHS done, while the work on RHS
remaining
End position unknown
19
Bottom-Up Parsing (pictorial representation)


  • S -gt NP12 VP23
  • People Laugh
  • 1 2
    3
  • N12

    N23
  • V12

    V23
  • NP12 -gt N12
    NP23 -gt N23
  • VP12 -gt V12
    VP23 -gt V23
  • S1? -gt NP12 VP2?

20
Problem with Top-Down Parsing
  • Left Recursion
  • Suppose you have A-gt AB rule.
  • Then we will have the expansion as follows
  • ((A)K) -gt ((AB)K) -gt ((ABB)K) ..

21
Combining top-down and bottom-up strategies
22
Top-Down Bottom-Up Chart Parsing
  • Combines advantages of top-down bottom-up
    parsing.
  • 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

23
Transitive Closure
  • People laugh
  • 1 2 3
  • S ??NP VP NP ?N? VP ? V ?
  • NP ??DT N S ? NP?VP S ? NP VP ?
  • NP ??N VP ??V ADV success
  • VP ??V

24
Arcs in Parsing
  • Each arc represents a chart which records
  • Completed work (left of ?)
  • Expected work (right of ?)

25
Example
  • People laugh loudly
  • 1 2 3 4
  • 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

26
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 2nd
    3rd sentence.

27
Prepositional Phrase (PP) Attachment Problem
  • V NP1 P NP2
  • (Here P means preposition)
  • NP2 attaches to NP1 ?
  • or NP2 attaches to V ?

28
Parse Trees for a Structurally Ambiguous Sentence
  • Let the grammar be
  • S ? NP VP
  • NP ? DT N DT N PP
  • PP ? P NP
  • VP ? V NP PP V NP
  • For the sentence,
  • I saw a boy with a telescope

29
Parse Tree - 1
S
NP
VP
N
V
NP
Det
N
PP
saw
I
P
NP
a
boy
Det
N
with
a
telescope
30
Parse Tree -2
S
NP
VP
PP
N
V
NP
P
NP
Det
N
saw
I
Det
N
with
a
boy
a
telescope
About PowerShow.com