Upload
others
View
9
Download
0
Embed Size (px)
Citation preview
Dynamic Programming for
Linear-Time Incremental Parsing
Liang HuangInformation Sciences Institute
University of Southern California
(Joint work with Kenji Sagae, USC/ICT)
JHU CLSP Seminar September 14, 2010
Remembering Fred Jelinek (1932-2010)
Prof. Jelinek hosted my visit and this talk on his last day.
He was very supportive of this work, which is related to his work on structured language models, and I dedicate my work to his memory.
DP for Incremental Parsing
Ambiguity and Incrementality
3
• NLP is (almost) all about ambiguity resolution
• human-beings resolve ambiguity incrementally
DP for Incremental Parsing
Ambiguity and Incrementality
3
One morning in Africa, I shot an elephant in my pajamas;
• NLP is (almost) all about ambiguity resolution
• human-beings resolve ambiguity incrementally
DP for Incremental Parsing
Ambiguity and Incrementality
3
One morning in Africa, I shot an elephant in my pajamas;
how he got into my pajamas I’ll never know.
• NLP is (almost) all about ambiguity resolution
• human-beings resolve ambiguity incrementally
DP for Incremental Parsing
Ambiguity and Incrementality
3
One morning in Africa, I shot an elephant in my pajamas;
how he got into my pajamas I’ll never know.
• NLP is (almost) all about ambiguity resolution
• human-beings resolve ambiguity incrementally
DP for Incremental Parsing
Ambiguity and Incrementality
3
One morning in Africa, I shot an elephant in my pajamas;
how he got into my pajamas I’ll never know.
• NLP is (almost) all about ambiguity resolution
• human-beings resolve ambiguity incrementally
CS 562 - Intro
Ambiguities in Translation
4
CS 562 - Intro
Ambiguities in Translation
4
CS 562 - Intro
Ambiguities in Translation
4
Google translate: carefully slide
CS 562 - Intro
Ambiguities in Translation
4
Google translate: carefully slide
CS 562 - Intro
Ambiguities in Translation
4
Google translate: carefully slide
CS 562 - Intro
If you are stolen...
5
CS 562 - Intro
If you are stolen...
5
Google translate: Once the theft to the police
CS 562 - Intro
or even...
6
CS 562 - Intro
or even...
6clear evidence that NLP is used in real life!
DP for Incremental Parsing
Ambiguities in Parsing
I feed cats nearby in the garden ...
• let’s focus on dependency structures for simplicity
• ambiguous attachments of nearby and in
• ambiguity explodes exponentially with sentence length
• must design efficient (polynomial) search algorithm
• typically using dynamic programming (DP); e.g. CKY
7
DP for Incremental Parsing
Ambiguities in Parsing
I feed cats nearby in the garden ...
• let’s focus on dependency structures for simplicity
• ambiguous attachments of nearby and in
• ambiguity explodes exponentially with sentence length
• must design efficient (polynomial) search algorithm
• typically using dynamic programming (DP); e.g. CKY
7
DP for Incremental Parsing
Ambiguities in Parsing
I feed cats nearby in the garden ...
• let’s focus on dependency structures for simplicity
• ambiguous attachments of nearby and in
• ambiguity explodes exponentially with sentence length
• must design efficient (polynomial) search algorithm
• typically using dynamic programming (DP); e.g. CKY
7
DP for Incremental Parsing
Ambiguities in Parsing
I feed cats nearby in the garden ...
• let’s focus on dependency structures for simplicity
• ambiguous attachments of nearby and in
• ambiguity explodes exponentially with sentence length
• must design efficient (polynomial) search algorithm
• typically using dynamic programming (DP); e.g. CKY
7
DP for Incremental Parsing
But full DP is too slow...
8
I feed cats nearby in the garden ...
• full DP (like CKY) is too slow (cubic-time)
• while human parsing is fast & incremental (linear-time)
DP for Incremental Parsing
But full DP is too slow...
8
I feed cats nearby in the garden ...
• full DP (like CKY) is too slow (cubic-time)
• while human parsing is fast & incremental (linear-time)
• how about incremental parsing then?
• yes, but only with greedy search (accuracy suffers)
• explores tiny fraction of trees (even w/ beam search)
DP for Incremental Parsing
But full DP is too slow...
8
I feed cats nearby in the garden ...
• full DP (like CKY) is too slow (cubic-time)
• while human parsing is fast & incremental (linear-time)
• how about incremental parsing then?
• yes, but only with greedy search (accuracy suffers)
• explores tiny fraction of trees (even w/ beam search)
• can we combine the merits of both approaches?
• a fast, incremental parser with dynamic programming?
• explores exponentially many trees in linear-time?
DP for Incremental Parsing
Linear-Time Incremental DP
9
greedy search
principled search
incremental parsing (e.g. shift-reduce)
(Nivre 04; Collins/Roark 04; ...)
this work:fast shift-reduce parsing with dynamic programming
full DP(e.g. CKY)
(Eisner 96; Collins 99; ...)
fast(linear-time)
slow(cubic-time)
☹☺☺
☹
DP for Incremental Parsing
Big Picture
10
natural languages
programming languages
human
computer
☺psycholinguistics ☹
☹NLP☺
compiler theory(LR, LALR, ...)
DP for Incremental Parsing
Big Picture
10
natural languages
programming languages
human
computer
☺psycholinguistics ☹
☹NLP☺
compiler theory(LR, LALR, ...)
DP for Incremental Parsing
Preview of the Results• very fast linear-time dynamic programming parser
• best reported dependency accuracy on PTB/CTB
• explores exponentially many trees (and outputs forest)
11
0
0.2
0.4
0.6
0.8
1
1.2
1.4
0 10 20 30 40 50 60 70
parsing time (secs)
sentence length
DP for Incremental Parsing
Preview of the Results• very fast linear-time dynamic programming parser
• best reported dependency accuracy on PTB/CTB
• explores exponentially many trees (and outputs forest)
11
Ch
arn
iak
Ber
kele
yM
ST
this work 0
0.2
0.4
0.6
0.8
1
1.2
1.4
0 10 20 30 40 50 60 70
parsing time (secs)
sentence length
DP for Incremental Parsing
Preview of the Results• very fast linear-time dynamic programming parser
• best reported dependency accuracy on PTB/CTB
• explores exponentially many trees (and outputs forest)
11
Ch
arn
iak
Ber
kele
yM
ST
this work 0
0.2
0.4
0.6
0.8
1
1.2
1.4
0 10 20 30 40 50 60 70
parsing time (secs)
sentence length
100
102
104
106
108
1010
0 10 20 30 40 50 60 70number of trees explored
sentence length
DP: exponen
tial
non-DP beam search
DP for Incremental Parsing
Outline
• Motivation
• Incremental (Shift-Reduce) Parsing
• Dynamic Programming for Incremental Parsing
• Experiments
12
DP for Incremental Parsing
I feed cats ...
feed cats nearby ...
cats nearby in ...
cats nearby in ...
nearby in the ...
nearby in the ...
in the garden ...
Shift-Reduce Parsing
13
action stack queue
I feed cats nearby in the garden.
0 -
DP for Incremental Parsing
I feed cats ...
feed cats nearby ...
cats nearby in ...
cats nearby in ...
nearby in the ...
nearby in the ...
in the garden ...
Shift-Reduce Parsing
14
action stack queue
I feed cats nearby in the garden.
I
0 -
1 shift
DP for Incremental Parsing
I feed cats ...
feed cats nearby ...
cats nearby in ...
cats nearby in ...
nearby in the ...
nearby in the ...
in the garden ...
Shift-Reduce Parsing
15
action stack queue
I feed cats nearby in the garden.
I feed
I
0 -
1 shift
2 shift
DP for Incremental Parsing
I feed cats ...
feed cats nearby ...
cats nearby in ...
cats nearby in ...
nearby in the ...
nearby in the ...
in the garden ...
Shift-Reduce Parsing
16
action stack queue
I feed cats nearby in the garden.
I feed
I
feedI
0 -
1 shift
2 shift
3 l-reduce
DP for Incremental Parsing
I feed cats ...
feed cats nearby ...
cats nearby in ...
cats nearby in ...
nearby in the ...
nearby in the ...
in the garden ...
Shift-Reduce Parsing
17
action stack queue
I feed cats nearby in the garden.
I feed
I
feedI feed cats
I
0 -
1 shift
2 shift
3 l-reduce
4 shift
DP for Incremental Parsing
Shift-Reduce Parsing
18
action stack queue
I feed cats nearby in the garden.
I feed cats ...
feed cats nearby ...
cats nearby in ...
cats nearby in ...
nearby in the ...
nearby in the ...
in the garden ...
I feed
I
feedI feed cats
I feed
I cats
0 -
1 shift
2 shift
3 l-reduce
4 shift
5a r-reduce
DP for Incremental Parsing
Shift-Reduce Parsing
19
action stack queue
I feed cats ...
feed cats nearby ...
cats nearby in ...
cats nearby in ...
nearby in the ...
nearby in the ...
in the garden ...
I feed cats nearby in the garden.
I feed
I
feedI feed cats
I feed
I cats
feed cats nearbyI
0 -
1 shift
2 shift
3 l-reduce
4 shift
5a r-reduce
5b shift
DP for Incremental Parsing
Shift-Reduce Parsing
20
action stack queue
shift-reduceconflict
I feed cats nearby in the garden.
I feed cats ...
feed cats nearby ...
cats nearby in ...
cats nearby in ...
nearby in the ...
nearby in the ...
in the garden ...
I feed
I
feedI feed cats
I feed
I cats
feed cats nearbyI
0 -
1 shift
2 shift
3 l-reduce
4 shift
5a r-reduce
5b shift
DP for Incremental Parsing
Choosing Parser Actions
• score each action using features f and weights w
• features are drawn from a local window
• abstraction (or signature) of a state -- this inspires DP!
• weights trained by structured perceptron (Collins 02)
21
... s2 s1 s0 q0 q1 ...
← stack queue →← stack queue →
features:(s0.w, s0.rc, q0, ...) = (cats, nearby, in, ...)
... feed cats I nearby
in the garden ...
DP for Incremental Parsing
Greedy Search
22
• each state => three new states (shift, l-reduce, r-reduce)
• search space should be exponential
• greedy search: always pick the best next state
DP for Incremental Parsing
Greedy Search
23
• each state => three new states (shift, l-reduce, r-reduce)
• search space should be exponential
• greedy search: always pick the best next state
DP for Incremental Parsing
Beam Search
24
• each state => three new states (shift, l-reduce, r-reduce)
• search space should be exponential
• beam search: always keep top-b states
DP for Incremental Parsing
Dynamic Programming• each state => three new states (shift, l-reduce, r-reduce)
• key idea of DP: share common subproblems
• merge equivalent states => polynomial space
25
DP for Incremental Parsing
Dynamic Programming• each state => three new states (shift, l-reduce, r-reduce)
• key idea of DP: share common subproblems
• merge equivalent states => polynomial space
26
“graph-structured stack” (Tomita, 1988)
DP for Incremental Parsing
Dynamic Programming• each state => three new states (shift, l-reduce, r-reduce)
• key idea of DP: share common subproblems
• merge equivalent states => polynomial space
27
“graph-structured stack” (Tomita, 1988)
DP for Incremental Parsing
Dynamic Programming• each state => three new states (shift, l-reduce, r-reduce)
• key idea of DP: share common subproblems
• merge equivalent states => polynomial space
27
“graph-structured stack” (Tomita, 1988)
each DP state corresponds toexponentially many non-DP states
DP for Incremental Parsing
Dynamic Programming• each state => three new states (shift, l-reduce, r-reduce)
• key idea of DP: share common subproblems
• merge equivalent states => polynomial space
28
“graph-structured stack” (Tomita, 1988)
100
102
104
106
108
1010
0 10 20 30 40 50 60 70number of trees explored
sentence length
DP: exponen
tial
non-DP beam search
each DP state corresponds toexponentially many non-DP states
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed cats nearby in the gardenI
• feed cats nearby in the gardenI
29
... s2 s1 s0 q0 q1 ...
← stack queue →
... catsre
feed... feedIshsh
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed cats nearby in the gardenI
• feed cats nearby in the gardenI
29
... s2 s1 s0 q0 q1 ...
← stack queue →
... catsre
feed... feedIshsh assume features only
look at root of s0
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed cats nearby in the gardenI
• feed cats nearby in the gardenI
29
... s2 s1 s0 q0 q1 ...
← stack queue →
... catsre
feed... feedIshsh assume features only
look at root of s0
two states are equivalent if they agree on root of s0
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed cats nearby in the gardenI
• feed cats nearby in the gardenI
29
... s2 s1 s0 q0 q1 ...
← stack queue →
... catsre
feed... feedIshsh assume features only
look at root of s0
two states are equivalent if they agree on root of s0
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed cats nearby in the gardenI
• feed cats nearby in the gardenI cats
30
... s2 s1 s0 q0 q1 ...
← stack queue →
sh
re... cats
... nearby
... feed
...
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed cats nearby in the gardenI
• feed cats nearby in the gardenI cats
30
... s2 s1 s0 q0 q1 ...
← stack queue →
sh
re... cats
... nearby
... feed
...
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed cats nearby in the gardenI nearby
• feed cats nearby in the gardenI cats
31
... s2 s1 s0 q0 q1 ...
← stack queue →
sh
re... cats
... nearby
... feed
re... cats
sh... nearby
...
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed in the gardenI cats nearby
• feed in the gardenI cats nearby
32
... s2 s1 s0 q0 q1 ...
← stack queue →
sh
re... cats
... nearby
... feed
re... cats ... feedre
... feedresh
... nearby
...
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed in the gardenI cats nearby
• feed in the gardenI cats nearby
32
... s2 s1 s0 q0 q1 ...
← stack queue →
equivalent if featuresonly look at s0 and q0
sh
re... cats
... nearby
... feed
re... cats ... feedre
... feedresh
... nearby
...
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed in the gardenI cats nearby
• feed in the gardenI cats nearby
33
... s2 s1 s0 q0 q1 ...
← stack queue →
sh
re... cats
... nearby
... feed
re... cats re
... feedresh
... nearby
...
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed in the gardenI cats nearby
• feed in the gardenI cats nearby
33
... s2 s1 s0 q0 q1 ...
← stack queue →
sh
re... cats
... nearby
... feed
re... cats re
... feedresh
... nearby
...
(local) ambiguity-packing!
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed in the gardenI cats nearby
• feed in the gardenI cats nearby
34
... s2 s1 s0 q0 q1 ...
← stack queue →
sh
re... cats
... nearby
... feed
re... cats re
... feedresh
... nearby... in
sh
...
DP for Incremental Parsing
Merging Equivalent States
• two states are equivalent if they agree on features
• because same features guarantee same cost
• shift-reduce conflict:
• feed in the gardenI cats nearby
• feed in the gardenI cats nearby
34
... s2 s1 s0 q0 q1 ...
← stack queue →
sh
re... cats
... nearby
... feed
re... cats re
... feedresh
... nearby... in
sh
...
graph-structured stack
DP for Incremental Parsing
Theory: Polynomial-Time DP
• this DP is exact and polynomial-time if features are:
• a) bounded -- for polynomial time
• features can only look at a local window
• b) monotonic -- for correctness (optimal substructure)
• features should draw no more info from trees farther away from stack top than from trees closer to top
• both are intuitive: a) always true; b) almost always true35
... s2 s1 s0 q0 q1 ...
← stack queue →
DP for Incremental Parsing
Theory: Monotonic History• related: grammar refinement by annotation (Johnson, 1998)
• annotate vertical context history (e.g., parent)
• monotonicity: can’t annotate grand-parent without annotating the parent (otherwise DP would fail)
• our features: left-context history instead of vertical-context
• similarly, can’t annotate s2 without annotating s1
• but we can always design “minimum monotonic superset”
36
parent
grand-parent
s1
s2
s0
stack
DP for Incremental Parsing
Related Work
• Graph-Structured Stack (Tomita 88): Generalized LR
• GSS is just a chart viewed from left to right (e.g. Earley 70)
• this line of work started w/ Lang (1974); stuck since 1990
• b/c explicit LR table is impossible with modern grammars
• Jelinek (2004) independently rediscovered GSS
37
DP for Incremental Parsing
Related Work
• Graph-Structured Stack (Tomita 88): Generalized LR
• GSS is just a chart viewed from left to right (e.g. Earley 70)
• this line of work started w/ Lang (1974); stuck since 1990
• b/c explicit LR table is impossible with modern grammars
• Jelinek (2004) independently rediscovered GSS
• We revived and advanced this line of work in two aspects
• theoretical: implicit LR table based on features
• merge and split on-the-fly; no pre-compilation needed
• monotonic feature functions guarantee correctness (new)
• practical: achieved linear-time performance with pruning
37
DP for Incremental Parsing
Jelinek (2004)
38In: M. Johnson, S. Khudanpur, M. Ostendorf, and R. Rosenfeld (eds.): Mathematical Foundations of Speech and Language Processing, 2004
DP for Incremental Parsing
Jelinek (2004)
38
graph-structured stack!
In: M. Johnson, S. Khudanpur, M. Ostendorf, and R. Rosenfeld (eds.): Mathematical Foundations of Speech and Language Processing, 2004
DP for Incremental Parsing
Jelinek (2004)
38
I don’t know anything about this paper...
graph-structured stack!
In: M. Johnson, S. Khudanpur, M. Ostendorf, and R. Rosenfeld (eds.): Mathematical Foundations of Speech and Language Processing, 2004
DP for Incremental Parsing
Jelinek (2004)• structured language model as graph-structured stack
39see also (Chelba and Jelinek, 98; 00; Xu, Chelba, Jelinek, 02)
DP for Incremental Parsing
Jelinek (2004)• structured language model as graph-structured stack
39
pSLM( a | has, show)
p3gram( a | its, host)
see also (Chelba and Jelinek, 98; 00; Xu, Chelba, Jelinek, 02)
Experiments
DP for Incremental Parsing
Speed Comparison
41
• 5 times faster with the same parsing accuracy
time (hours)
non-DPDP
DP for Incremental Parsing
Correlation of Search and Parsing
42
92.2
92.3
92.4
92.5
92.6
92.7
92.8
92.9
93
93.1
2365 2370 2375 2380 2385 2390 2395
dependency accuracy
average model score
DPnon-DP
• better search quality <=> better parsing accuracy
DP for Incremental Parsing
Search Space: Exponential
43
100
102
104
106
108
1010
0 10 20 30 40 50 60 70number of trees explored
sentence length
DP: exponen
tial
non-DP: fixed (beam-width)num
ber
of t
rees
exp
lore
d
DP for Incremental Parsing
N-Best / Forest Oracles
44
DP forest oracle (98.15)
DP k-best in forest
non-
DP
k-bes
t
in be
am
DP for Incremental Parsing
Better Search => Better Learning
45
• DP leads to faster and better learning w/ perceptron
DP for Incremental Parsing
Learning Details: Early Updates• greedy search: update at first error
• beam search: update when gold is pruned (Collins/Roark 04)
• DP search: also update when gold is “merged” (new!)
• b/c we know gold can’t make to the top again
46
DP non-DP
DP for Incremental Parsing
Parsing Time vs. Sentence Length
47
• parsing speed (scatter plot) compared to other parsers
0
0.2
0.4
0.6
0.8
1
1.2
1.4
0 10 20 30 40 50 60 70
parsing time (secs)
sentence length
DP for Incremental Parsing
Parsing Time vs. Sentence Length
47
• parsing speed (scatter plot) compared to other parsers
Ch
arn
iak
Ber
kele
yM
ST
this work
0
0.2
0.4
0.6
0.8
1
1.2
1.4
0 10 20 30 40 50 60 70
parsing time (secs)
sentence length
DP for Incremental Parsing
Parsing Time vs. Sentence Length
47
• parsing speed (scatter plot) compared to other parsers
Ch
arn
iak
Ber
kele
yM
ST
this work
0
0.2
0.4
0.6
0.8
1
1.2
1.4
0 10 20 30 40 50 60 70
parsing time (secs)
sentence length
O(n2)
O(n)
O(n2.4)O(n2.5)
DP for Incremental Parsing
Final Results• much faster than major parsers (even with Python!)
• first linear-time incremental dynamic programming parser
• best reported dependency accuracy on Penn Treebank
time complexity trees searched
0.12 O(n2) exponential
- O(n4) exponential
0.11 O(n) constant
0.04 O(n) exponential
0.49 O(n2.5) exponential
0.21 O(n2.4) exponential
McDonald et al 05 - MST
Koo et al 08 baseline*
Zhang & Clark 08 single
this work
Charniak 00
Petrov & Klein 07
89 91 93
92.4
92.5
92.1
91.4
92.0
90.2
DP for Incremental Parsing
Final Results• much faster than major parsers (even with Python!)
• first linear-time incremental dynamic programming parser
• best reported dependency accuracy on Penn Treebank
time complexity trees searched
0.12 O(n2) exponential
- O(n4) exponential
0.11 O(n) constant
0.04 O(n) exponential
0.49 O(n2.5) exponential
0.21 O(n2.4) exponential
McDonald et al 05 - MST
Koo et al 08 baseline*
Zhang & Clark 08 single
this work
Charniak 00
Petrov & Klein 07
89 91 93
92.4
92.5
92.1
91.4
92.0
90.2
DP for Incremental Parsing
Final Results• much faster than major parsers (even with Python!)
• first linear-time incremental dynamic programming parser
• best reported dependency accuracy on Penn Treebank
time complexity trees searched
0.12 O(n2) exponential
- O(n4) exponential
0.11 O(n) constant
0.04 O(n) exponential
0.49 O(n2.5) exponential
0.21 O(n2.4) exponential
McDonald et al 05 - MST
Koo et al 08 baseline*
Zhang & Clark 08 single
this work
Charniak 00
Petrov & Klein 07
89 91 93
92.4
92.5
92.1
91.4
92.0
90.2
*at this ACL: Koo & Collins 10: 93.0 with O(n4)
DP for Incremental Parsing
Final Results on Chinese
• also the best parsing accuracy on Chinese
• Penn Chinese Treebank (CTB 5)
• all numbers below use gold-standard POS tags
49
Duan et al. 2007
Zhang & Clark 08 (single)
this work
70 85
78.3
76.7
73.7
85.5
84.7
84.4
85.2
84.3
83.9 wordnon-rootroot
DP for Incremental Parsing
Conclusion
50
greedy search
principled search
incremental parsing
(e.g. shift-reduce)
☺✓full dynamic
programming(e.g. CKY)
fast(linear-time)
slow(cubic-time)
DP for Incremental Parsing
Conclusion
50
greedy search
principled search
incremental parsing
(e.g. shift-reduce)
☺✓full dynamic
programming(e.g. CKY)
fast(linear-time)
slow(cubic-time)
linear-timeshift-reduce parsing
w/ dynamic programming
DP for Incremental Parsing
Zoom out to Big Picture...
51
natural languages
programming languages
human
computer
☺psycholinguistics ☹
☺?NLP
☺ compiler theory
still a long way to go...
DP for Incremental Parsing
Thank You
• a general theory of DP for shift-reduce parsing
• as long as features are bounded and monotonic
• fast, accurate DP parser release coming soon:
• http://www.isi.edu/~lhuang
• future work
• adapt to constituency parsing (straightforward)
• other grammar formalisms like CCG and TAG
• integrate POS tagging into the parser
• integrate semantic interpretation52
DP for Incremental Parsing
How I was invited to give this talk• Fred attended ACL 2010 in Sweden
• Mark Johnson mentioned to him about this work
• Fred saw my co-author Kenji Sagae giving the talk
• but didn’t realize it was Kenji; he thought it was me
• he emailed me (but mis-spelled my name in the address)
• not getting a reply, he asked Kevin Knight to “forward it to Liang Haung or his student Sagae.”
• Fred complained that my paper is very hard to read“As you can see, I am completely confused!” And he was right.
• finally he said “come here to give a talk and explain it.”53