Parsing German with Latent Variable Grammars Slav Petrov and Dan Klein UC Berkeley.

Parsing German with Latent Variable Grammars

Slav Petrov and Dan Klein

UC Berkeley

The Game of Designing a Grammar

Annotation refines base treebank symbols to improve statistical fit of the grammar Parent annotation [Johnson ’98] Head lexicalization [Collins ’99, Charniak ’00] Automatic clustering?

Previous Work:Manual Annotation

Manually split categories NP: subject vs object DT: determiners vs demonstratives IN: sentential vs prepositional

Advantages: Fairly compact grammar Linguistic motivations

Disadvantages: Performance leveled out Manually annotated

[Klein & Manning ’03]

Model F1

Naïve Treebank Grammar 72.6

Klein & Manning ’03 86.3

Previous Work:Automatic Annotation Induction

Advantages: Automatically learned:

Label all nodes with latent variables.

Same number k of subcategories for all categories.

Disadvantages: Grammar gets too large Most categories are

oversplit while others are undersplit.

[Matsuzaki et. al ’05, Prescher ’05]

Model F1

Klein & Manning ’03 86.3

Matsuzaki et al. ’05 86.7

[Petrov, Barrett, Thibaux & Klein

in ACL’06]

[Petrov & Klein in NAACL’07]

Overview

Learning: Hierarchical Training Adaptive Splitting Parameter Smoothing

Inference: Coarse-To-Fine Decoding Variational Approximation

German Analysis

Forward

Learning Latent Annotations

EM algorithm:

X1

X2X7X4

X5 X6X3

He was right

.

Brackets are known Base categories are known Only induce subcategories

Just like Forward-Backward for HMMs. Backward

k=16k=8

k=4

k=2

k=160

65

70

75

80

85

90

50 250 450 650 850 1050 1250 1450 1650

Total Number of grammar symbols

Parsing accuracy (F1)

Starting PointLimit of computational resources

Refinement of the DT tag

DT-1 DT-2 DT-3 DT-4

DT

Refinement of the DT tagDT

Hierarchical Refinement of the DT tag

DT

Hierarchical Estimation Results

74

76

78

80

82

84

86

88

90

100 300 500 700 900 1100 1300 1500 1700

Total Number of grammar symbols

Parsing accuracy (F1)

Model F1

Baseline 87.3

Hierarchical Training 88.4

Refinement of the , tag

Splitting all categories the same amount is wasteful:

The DT tag revisited

Oversplit?

Adaptive Splitting

Want to split complex categories more Idea: split everything, roll back splits which

were least useful

Adaptive Splitting

Want to split complex categories more Idea: split everything, roll back splits which

were least useful

Adaptive Splitting

Evaluate loss in likelihood from removing each split =

Data likelihood with split reversed

Data likelihood with split No loss in accuracy when 50% of the splits are

reversed.

Adaptive Splitting Results

74

76

78

80

82

84

86

88

90

100 300 500 700 900 1100 1300 1500 1700

Total Number of grammar symbols

Parsing accuracy (F1)

50% Merging

Hierarchical Training

Flat TrainingModel F1

Previous 88.4

With 50% Merging 89.5

0

5

10

15

20

25

30

35

VP NP PP AP S

CNP AVP PN CAP

CS CVP

VZ CCP NM CPP MTA CVZ

AA ISU

VROOT CAVP CAC

CH CO DL ROOT

Number of Phrasal Subcategories

0

5

10

15

20

25

30

35

NE

VVFIN ADJA NN ADV

ADJD VVPP APPR VVINF CARD ART PIS PIAT

PPER KON $[

PROAV VAFIN PDS

APPRAR PPOSAT

$.

PDAT PRELS PTKVZ VVIZU VAINF KOUS VMFIN

FM VAPP

KOKOM PWAV

PWS KOUI TRUNC

XY

PTKZU PWAT VVIMP NNE

PRELAT PTKNEG

APZR

Number of Lexical Subcategories

Smoothing

Heavy splitting can lead to overfitting Idea: Smoothing allows us to pool

statistics

Linear Smoothing

74

76

78

80

82

84

86

88

90

100 300 500 700 900 1100

Total Number of grammar symbols

Parsing accuracy (F1)50% Merging and Smoothing

50% Merging

Hierarchical Training

Flat Training

Model F1

Previous 89.5

With Smoothing 90.7

Result Overview

Coarse-to-Fine Parsing[Goodman ‘97, Charniak&Johnson ‘05]

Coarse grammarNP … VP

NP-dog NP-catNP-apple VP-run NP-eat…

Refined grammar

…

TreebankParse

Pru

ne

NP-17 NP-12NP-1 VP-6VP-31…

Refined grammar

…

Parse

Hierarchical Pruning

Consider the span 5 to 12:

… QP NP VP …coarse:

split in two: … QP1

QP2

NP1 NP2 VP1 VP2 …

… QP1

QP1

QP3

QP4

NP1 NP2 NP3 NP4 VP1 VP2 VP3 VP4 …split in four:

split in eight: … … … … … … … … … … … … … … … … …

Intermediate Grammars

X-Bar=G0

G=

G1

G2

G3

G4

G5

G6

Lea

rning DT1 DT2 DT3 DT4 DT5 DT6 DT7 DT8

DT1 DT2 DT3 DT4

DT1

DT

DT2

State Drift (DT tag)

somesomethisthisThatThat thesethese

That this some

the

these

this some

that

That this some

the

these

this some

that

……………… …… ……………… …… somesomethesethisThatThis thatthat EM

G1

G2

G3

G4

G5

G6

Lea

rning

G1

G2

G3

G4

G5

G6

Lea

rning

Projected Grammars

X-Bar=G0

G=

Pro

jectio

n i

0(G)

1(G)

2(G)

3(G)

4(G)

5(G)G

Bracket Posteriors (after G0)

Bracket Posteriors (after G1)

Bracket Posteriors (Movie)(Final Chart)

Bracket Posteriors (Best Tree)

Parse Selection

Computing most likely unsplit tree is NP-hard: Settle for best derivation. Rerank n-best list. Use alternative objective function / Variational Approximation.

Parses:

-1

-1

-2

-2

-1

-1

-1Derivations:

-1

-2

-1

-1

-2

-1

-2

Efficiency Results

Berkeley Parser: 15 min Implemented in Java

Charniak & Johnson ‘05 Parser 19 min Implemented in C

Accuracy Results

≤ 40 words

F1

all

F1

EN

G

Charniak&Johnson ‘05 (generative) 90.1 89.6

This Work 90.6 90.1

GE

R

Dubey ‘05 76.3 -

This Work 80.8 80.1

CH

N

Chiang et al. ‘02 80.0 76.6

This Work 86.3 83.4

Parsing German Shared Task

Two Pass Parsing Determine constituency structure (F1: 85/94) Assign grammatical functions

One Pass Approach Treat categories+grammatical functions as

labels

Parsing German Shared Task

Two Pass Parsing Determine constituency structure Assign grammatical functions

One Pass Approach Treat categories+grammatical functions as

labels

Development Set Results

Shared Task Results

Part-of-speech splits

Linguistic Candy

Conclusions

Split & Merge Learning Hierarchical Training Adaptive Splitting Parameter Smoothing

Hierarchical Coarse-to-Fine Inference Projections Marginalization

Multi-lingual Unlexicalized Parsing

Thank You!

Parser is avaliable athttp://nlp.cs.berkeley.edu