parsing david kauchak cs457 – fall 2011 some slides adapted from ray mooney
TRANSCRIPT
![Page 1: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/1.jpg)
PARSINGDavid Kauchak
CS457 – Fall 2011some slides adapted from Ray Mooney
![Page 2: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/2.jpg)
Admin
Survey http://www.surveymonkey.com/s/TF75YJD
![Page 3: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/3.jpg)
Admin
Graduate school? Good time for last-minute programming
contest practice sessions? Assignment 2 grading
![Page 4: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/4.jpg)
Admin
Java programming What is a package?
Why are they important? When should we use them? How do we define them?
Interfaces: say my interface has a method:
public void myMethod(); If I’m implementing the interface is it ok to:
public void myMethod() throws SomeCheckedException
![Page 5: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/5.jpg)
Parsing
Given a CFG and a sentence, determine the possible parse tree(s)
S -> NP VPNP -> PRPNP -> N PPVP -> V NPVP -> V NP PPPP -> IN NPRP -> IV -> eatN -> sushiN -> tunaIN -> with
I eat sushi with tuna
![Page 6: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/6.jpg)
Parsing
Top-down parsing start at the top (usually S) and apply rules matching left-hand sides and replacing with right-
hand sides
Bottom-up parsing start at the bottom (i.e. words) and build the parse tree up
from there matching right-hand sides and replacing with left-hand
sides
![Page 7: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/7.jpg)
CKY
First grammar must be converted to Chomsky normal form (CNF) We’ll allow all unary rules, though
Parse bottom-up storing phrases formed from all substrings in a triangular table (chart)
![Page 8: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/8.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
what does this cell represent?
![Page 9: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/9.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
all constituents spanning 1-3 or “the man with”
![Page 10: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/10.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
how could we figure this out?
![Page 11: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/11.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
Key: rules are binary and only have two constituents on the right hand side
VP -> VB NPNP -> DT NN
![Page 12: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/12.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
See if we can make a new constituent combining any for “the” with any for “man with”
![Page 13: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/13.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
See if we can make a new constituent combining any for “the man” with any for “with”
![Page 14: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/14.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
?
![Page 15: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/15.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
See if we can make a new constituent combining any for “Film” with any for “the man with trust”
![Page 16: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/16.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
See if we can make a new constituent combining any for “Film the” with any for “man with trust”
![Page 17: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/17.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
See if we can make a new constituent combining any for “Film the man” with any for “with trust”
![Page 18: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/18.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
See if we can make a new constituent combining any for “Film the man with” with any for “trust”
![Page 19: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/19.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
What if our rules weren’t binary?
![Page 20: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/20.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
See if we can make a new constituent combining any for “Film” with any for “the man” with any for “with trust”
![Page 21: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/21.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
What order should we fill the entries in the chart?
![Page 22: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/22.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
What order should we traverse the entries in the chart?
![Page 23: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/23.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
From bottom to top, left to right
![Page 24: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/24.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Cell[i,j] contains allconstituents covering words i through j
Film the man with trust
Top-left along the diagonals moving to the right
![Page 25: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/25.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Film the man with trust S -> VP
VP -> VB NPVP -> VP2 PPVP2 -> VB NPNP -> DT NN NP -> NNNP -> NP PPPP -> IN NPDT -> theIN -> withVB -> filmVB -> manVB -> trustNN -> manNN -> filmNN -> trust
![Page 26: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/26.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Film the man with trust S -> VP
VP -> VB NPVP -> VP2 PPVP2 -> VB NPNP -> DT NN NP -> NNNP -> NP PPPP -> IN NPDT -> theIN -> withVB -> filmVB -> manVB -> trustNN -> manNN -> filmNN -> trust
NNNPVB
DT
VBNNNP
IN
VBNNNP
![Page 27: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/27.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Film the man with trust S -> VP
VP -> VB NPVP -> VP2 PPVP2 -> VB NPNP -> DT NN NP -> NNNP -> NP PPPP -> IN NPDT -> theIN -> withVB -> filmVB -> manVB -> trustNN -> manNN -> filmNN -> trust
DT
VBNNNP
IN
VBNNNP
NP
PP
NNNPVB
![Page 28: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/28.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Film the man with trust S -> VP
VP -> VB NPVP -> VP2 PPVP2 -> VB NPNP -> DT NN NP -> NNNP -> NP PPPP -> IN NPDT -> theIN -> withVB -> filmVB -> manVB -> trustNN -> manNN -> filmNN -> trust
DT
VBNNNP
IN
VBNNNP
NP
PP
VP2VPS
NP
NNNPVB
![Page 29: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/29.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Film the man with trust S -> VP
VP -> VB NPVP -> VP2 PPVP2 -> VB NPNP -> DT NN NP -> NNNP -> NP PPPP -> IN NPDT -> theIN -> withVB -> filmVB -> manVB -> trustNN -> manNN -> filmNN -> trust
DT
VBNNNP
IN
VBNNNP
NP
PP
VP2VPS
NP
NP
NNNPVB
![Page 30: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/30.jpg)
CKY parser: the chart
i=0
1
2
3
4
j= 0 1 2 3 4
Film the man with trust S -> VP
VP -> VB NPVP -> VP2 PPVP2 -> VB NPNP -> DT NN NP -> NNNP -> NP PPPP -> IN NPDT -> theIN -> withVB -> filmVB -> manVB -> trustNN -> manNN -> filmNN -> trust
DT
VBNNNP
IN
VBNNNP
NP
PP
VP2VPS
NP
NP
SVPVP2
NNNPVB
![Page 31: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/31.jpg)
CKY: some things to talk about After we fill in the chart, how do we know
if there is a parse? If there is an S in the upper right corner
What if we want an actual tree/parse?
![Page 32: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/32.jpg)
CKY: retrieving the parse
i=0
1
2
3
4
j= 0 1 2 3 4
DT
VBNNNP
IN
VBNNNP
NP
PP
VB2VPS
NP
NP
S
VP
S
VP
VB NP
Film the man with trust
NNNPVB
![Page 33: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/33.jpg)
CKY: retrieving the parse
i=0
1
2
3
4
j= 0 1 2 3 4
DT
VBNNNP
IN
VBNNNP
NP
PP
VB2VPS
NP
NP
S
VP
S
VP
VB NP
NP PP
Film the man with trust
NNNPVB
![Page 34: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/34.jpg)
CKY: retrieving the parse
i=0
1
2
3
4
j= 0 1 2 3 4
DT
VBNNNP
IN
VBNNNP
NP
PP
VB2VPS
NP
NP
S
VP
S
VP
VB NP
NP PP
Film the man with trust
DT NN IN NP
…
NNNPVB
![Page 35: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/35.jpg)
CKY: retrieving the parse
i=0
1
2
3
4
j= 0 1 2 3 4
DT
VBNNNP
IN
VBNNNP
NP
PP
VB2VPS
NP
NP
S
VP
Film the man with trust
Where do these arrows/references come from?
NNNPVB
![Page 36: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/36.jpg)
CKY: retrieving the parse
i=0
1
2
3
4
j= 0 1 2 3 4
DT
VBNNNP
IN
VBNNNP
NP
PP
VB2VPS
NP
NP
S
VP
Film the man with trust
To add a constituent in a cell, we’re applying a rule
The references represent the smaller constituents we used to build this constituent
S -> VPNNNPVB
![Page 37: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/37.jpg)
CKY: retrieving the parse
i=0
1
2
3
4
j= 0 1 2 3 4
DT
VBNNNP
IN
VBNNNP
NP
PP
VB2VPS
NP
NP
S
VP
Film the man with trust
To add a constituent in a cell, we’re applying a rule
The references represent the smaller constituents we used to build this constituent
VP -> VB NPNNNPVB
![Page 38: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/38.jpg)
CKY: retrieving the parse
i=0
1
2
3
4
j= 0 1 2 3 4
DT
VBNNNP
IN
VBNNNP
NP
PP
VB2VPS
NP
NP
S
VP
Film the man with trust
What about ambiguous parses?
NNNPVB
![Page 39: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/39.jpg)
CKY: retrieving the parse
We can store multiple derivations of each constituent
This representation is called a “parse forest”
It is often convenient to leave it in this form, rather than enumerate all possible parses. Why?
![Page 40: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/40.jpg)
CKY: some things to think about
S -> VPVP -> VB NPVP -> VB NP PPNP -> DT NN NP -> NN…
S -> VPVP -> VB NPVP -> VP2 PPVP2 -> VB NPNP -> DT NN NP -> NN…
Actual grammarCNF
We get a CNF parse tree but want one for the actual grammar
Ideas?
![Page 41: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/41.jpg)
Parsing ambiguity
I eat sushi with tuna
PRP
NP
V N IN N
PP
NP
VP
S
I eat sushi with tuna
PRP
NP
V N IN N
PPNP
VP
SS -> NP VPNP -> PRPNP -> N PPVP -> V NPVP -> V NP PPPP -> IN NPRP -> IV -> eatN -> sushiN -> tunaIN -> with
How can we decide between these?
![Page 42: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/42.jpg)
A Simple PCFG
S NP VP 1.0 VP V NP 0.7VP VP PP 0.3PP P NP 1.0P with 1.0V saw 1.0
NP NP PP 0.4 NP astronomers 0.1 NP ears 0.18 NP saw 0.04 NP stars 0.18 NP telescope 0.1
Probabilities!
![Page 43: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/43.jpg)
= 1.0 * 0.1 * 0.7 * 1.0 * 0.4 * 0.18 * 1.0 * 1.0 * 0.18= 0.0009072
= 1.0 * 0.1 * 0.3 * 0.7 * 1.0 * 0.18 * 1.0 * 1.0 * 0.18= 0.0006804
![Page 44: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/44.jpg)
Parsing with PCFGs
How does this change our CKY algorithm? We need to keep track of the probability of a
constituent How do we calculate the probability of a
constituent? Product of the PCFG rule times the product of the
probabilities of the sub-constituents (right hand sides)
Building up the product from the bottom-up What if there are multiple ways of deriving a
particular constituent? max: pick the most likely derivation of that
constituent
![Page 45: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/45.jpg)
Probabilistic CKY
Include in each cell a probability for each non-terminal
Cell[i,j] must retain the most probable derivation of each constituent (non-terminal) covering words i through j
When transforming the grammar to CNF, must set production probabilities to preserve the probability of derivations
![Page 46: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/46.jpg)
Probabilistic Grammar Conversion
S → NP VPS → Aux NP VP
S → VP
NP → Pronoun
NP → Proper-Noun
NP → Det NominalNominal → Noun
Nominal → Nominal NounNominal → Nominal PPVP → Verb
VP → Verb NPVP → VP PPPP → Prep NP
Original Grammar Chomsky Normal Form
S → NP VPS → X1 VPX1 → Aux NPS → book | include | prefer 0.01 0.004 0.006S → Verb NPS → VP PPNP → I | he | she | me 0.1 0.02 0.02 0.06NP → Houston | NWA 0.16 .04NP → Det NominalNominal → book | flight | meal | money 0.03 0.15 0.06 0.06Nominal → Nominal NounNominal → Nominal PPVP → book | include | prefer 0.1 0.04 0.06VP → Verb NPVP → VP PPPP → Prep NP
0.80.1
0.1
0.2 0.2 0.60.3
0.20.50.2
0.50.31.0
0.80.11.0
0.050.03
0.6
0.20.5
0.50.31.0
![Page 47: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/47.jpg)
Probabilistic CKY Parser
Book the flight through Houston
S :.01, VP:.1, Verb:.5 Nominal:.03Noun:.1
Det:.6
Nominal:.15Noun:.5
None
NP → Det Nominal 0.60
What is the probability of the NP?
![Page 48: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/48.jpg)
Probabilistic CKY Parser
Book the flight through Houston
S :.01, VP:.1, Verb:.5 Nominal:.03Noun:.1
Det:.6
Nominal:.15Noun:.5
None
NP:.6*.6*.15 =.054
NP → Det Nominal 0.60
![Page 49: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/49.jpg)
Probabilistic CKY Parser
Book the flight through Houston
S :.01, VP:.1, Verb:.5 Nominal:.03Noun:.1
Det:.6
Nominal:.15Noun:.5
None
NP:.6*.6*.15 =.054
VP → Verb NP 0.5
What is the probability of the VP?
![Page 50: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/50.jpg)
Probabilistic CKY Parser
Book the flight through Houston
S :.01, VP:.1, Verb:.5 Nominal:.03Noun:.1
Det:.6
Nominal:.15Noun:.5
None
NP:.6*.6*.15 =.054
VP:.5*.5*.054 =.0135
VP → Verb NP 0.5
![Page 51: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/51.jpg)
Probabilistic CKY Parser
Book the flight through Houston
S :.01, VP:.1, Verb:.5 Nominal:.03Noun:.1
Det:.6
Nominal:.15Noun:.5
None
NP:.6*.6*.15 =.054
VP:.5*.5*.054 =.0135
S:.05*.5*.054 =.00135
![Page 52: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/52.jpg)
Probabilistic CKY Parser
Book the flight through Houston
S :.01, VP:.1, Verb:.5 Nominal:.03Noun:.1
Det:.6
Nominal:.15Noun:.5
None
NP:.6*.6*.15 =.054
VP:.5*.5*.054 =.0135
S:.05*.5*.054 =.00135
None
None
None
Prep:.2
![Page 53: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/53.jpg)
Probabilistic CKY Parser
Book the flight through Houston
S :.01, VP:.1, Verb:.5 Nominal:.03Noun:.1
Det:.6
Nominal:.15Noun:.5
None
NP:.6*.6*.15 =.054
VP:.5*.5*.054 =.0135
S:.05*.5*.054 =.00135
None
None
None
Prep:.2
NP:.16PropNoun:.8
PP:1.0*.2*.16 =.032
![Page 54: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/54.jpg)
Probabilistic CKY Parser
Book the flight through Houston
S :.01, VP:.1, Verb:.5 Nominal:.03Noun:.1
Det:.6
Nominal:.15Noun:.5
None
NP:.6*.6*.15 =.054
VP:.5*.5*.054 =.0135
S:.05*.5*.054 =.00135
None
None
None
Prep:.2
NP:.16PropNoun:.8
PP:1.0*.2*.16 =.032
Nominal:.5*.15*.032=.0024
![Page 55: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/55.jpg)
Probabilistic CKY Parser
Book the flight through Houston
S :.01, VP:.1, Verb:.5 Nominal:.03Noun:.1
Det:.6
Nominal:.15Noun:.5
None
NP:.6*.6*.15 =.054
VP:.5*.5*.054 =.0135
S:.05*.5*.054 =.00135
None
None
None
Prep:.2
NP:.16PropNoun:.8
PP:1.0*.2*.16 =.032
Nominal:.5*.15*.032=.0024
NP:.6*.6* .0024 =.000864
![Page 56: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/56.jpg)
Probabilistic CKY Parser
Book the flight through Houston
S :.01, VP:.1, Verb:.5 Nominal:.03Noun:.1
Det:.6
Nominal:.15Noun:.5
None
NP:.6*.6*.15 =.054
VP:.5*.5*.054 =.0135
S:.05*.5*.054 =.00135
None
None
None
Prep:.2
NP:.16PropNoun:.8
PP:1.0*.2*.16 =.032
Nominal:.5*.15*.032=.0024
NP:.6*.6* .0024 =.000864
S:.05*.5* .000864 =.0000216
S:.03*.0135* .032 =.00001296
S → VP PP0.03S → Verb NP 0.05
![Page 57: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/57.jpg)
Probabilistic CKY Parser
Book the flight through Houston
S :.01, VP:.1, Verb:.5 Nominal:.03Noun:.1
Det:.6
Nominal:.15Noun:.5
None
NP:.6*.6*.15 =.054
VP:.5*.5*.054 =.0135
S:.05*.5*.054 =.00135
None
None
None
Prep:.2
NP:.16PropNoun:.8
PP:1.0*.2*.16 =.032
Nominal:.5*.15*.032=.0024
NP:.6*.6* .0024 =.000864
S:.0000216Pick most probableparse, i.e. take max tocombine probabilitiesof multiple derivationsof each constituent ineach cell
![Page 58: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/58.jpg)
Generic PCFG Limitations
PCFGs do not rely on specific words or concepts, only general structural disambiguation is possible (e.g. prefer to attach PPs to Nominals) Generic PCFGs cannot resolve syntactic
ambiguities that require semantics to resolve, e.g. ate with fork vs. meatballs
Smoothing/dealing with out of vocabulary
MLE estimates are not always the best
![Page 59: PARSING David Kauchak CS457 – Fall 2011 some slides adapted from Ray Mooney](https://reader036.vdocument.in/reader036/viewer/2022062421/56649dff5503460f94ae7c8f/html5/thumbnails/59.jpg)
Article discussion
Smarter Marketing and the Weak Link In Its Success http://searchenginewatch.com/article/2077636/Smarter-Marketing-and-the-Weak-
Link-In-Its-Success
What are the ethics involved with tracking user interests for the purpose of advertising? Is this something you find preferable to 'blind' marketing?
Is possible to get an accurate picture of someone’s interests from their web activity? What sources would be good for doing so?
How do you feel about websites that change content depending on the viewer? What are the implications of sites that behave this way?