27
Parser Adaptation and Projection with Quasi-Synchronous Grammar Features David A. Smith (UMass Amherst) Jason Eisner (Johns Hopkins) 1

Parser Adaptation and Projection with Quasi-Synchronous Grammar Features

  • Upload
    aislin

  • View
    49

  • Download
    0

Embed Size (px)

DESCRIPTION

Parser Adaptation and Projection with Quasi-Synchronous Grammar Features. David A. Smith (UMass Amherst) Jason Eisner (Johns Hopkins). This Talk in a Nutshell. now. or. never. Parser adaptation. Learned by Quasi-Synchronous Grammar. im. Anfang. in. the. beginning. Supervised. - PowerPoint PPT Presentation

Citation preview

Page 1: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

1

Parser Adaptation and Projection with Quasi-Synchronous Grammar Features

David A. Smith (UMass Amherst)Jason Eisner (Johns Hopkins)

Page 2: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

2

This Talk in a Nutshell

in the beginning

im Anfang

Parser projection

German Spanish

Unsupervised

10 100 1000

Supervised

now or never

Parser adaptation

Learned by Quasi-Synchronous Grammar

Page 3: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

3

Projecting Hidden Structure

Yarowsky & Ngai ‘01

Page 4: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

Projection

• Train with bitext• Parse one side• Align words• Project dependencies• Many to one links?• Invalid trees?• Hwa et al.: fix-up rules• Ganchev et al.: trust only

some links

Im Anfang war das Wort

In the beginning was the word

Page 5: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

Divergent Projection

Auf Fragediese bekommenichhabe leider Antwortkeine

I did not unfortunately receive an answer to this question

NULL

monotonicnull

head-swappingsiblings

Page 6: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

Free Translation

Tschernobyl könnte dann etwas später an die Reihe kommen

Then we could deal with Chernobyl some time later

Bad dependencies

Parent-ancestors?

NULL

Page 7: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

What’s Wrong with Projection?

• Hwa et al. Chinese data:– 38.1% F1 after projection– Only 26.3% with automatic

English parses– Cf. 35.9% for attach right!– 52.4% after fix-up rules

• Only 1-to-1 alignments:– 68% precision– 11% recall

Im Anfang war das Wort

In the beginning was the word

Page 8: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

8

EXCURSUS: DOMAIN ADAPTATION

Page 9: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

Projection

• Different languages• Similar meaning• Divergent syntaxIm Anfang war das Wort

In the beginning was the word

Page 10: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

Adaptation

• Same sentence• Divergent syntax

In the beginning was the word

In the beginning was the word

Page 11: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

11

A Lack of Coordination

now or never

Prague

now or never

Mel’čuk

now or never

CoNLL

now or never

MALT

Page 12: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

12

Prepositions and Auxiliaries

in the end in the end in the end

I have decided I have decided

Page 13: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

13

Adaptation Recipe

• Acquire (a few) trees in target domain• Run source-domain parser on training set• Train parser with features for:– Target tree alone– Source and target trees together

• Parse test set with:– Source-domain parser– Target-domain parser

Page 14: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

14

Why?

• Why not just modify source treebank?• Source parser could be a black box– Or rule based

• Vastly shorter training times with a small target treebank– Linguists can quickly explore alternatives– Don’t need dozens of rules

• Other benefits of stacking• And sometimes, divergence is very large

Page 15: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

15

MODEL STRUCTURE

Page 16: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

16

What We’re Modeling

s(t,t ',a,w,w') = θ i f i(t,w)i

∑ + θ jg j (t, t ',a,w,w')

j∑

in the beginning

im Anfang

t’w’

wt

a

p(t,a,w | t',w')

p(t | t',a,w,w')

This paper

Generative

Conditional

p(t,t ',a |w,w')Ongoing work

Page 17: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

17

Stacking

Model 1Input

Model 2

Model 2 has features for when to trust Model 1

Page 18: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

18

Quasi-Synchronous Grammar

• Generative or conditional monolingual model of target language or tree

• Condition target trees on source structure• Applications to– Alignment (D. Smith & Eisner ‘06)– Question Answering (Wang, N. Smith, Mitamura

‘07)– Paraphrase (Das & N. Smith ‘09)– Translation (Gimpel & N. Smith ‘09)

Page 19: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

Dependency Relations

+ “none of the above”

Page 20: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

21

EXPERIMENTS

Page 21: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

22

Experimental Plan

• Proof of concept on English dependency-convention adaptation

• Unsupervised projection– No target trees– Generative target model + QG features

• Supervised projection– Small number of target trees– Conditional target model + QG features

Page 22: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

23

Adaptation Results

Parsed source Gold source Parsed match Gold match0.6

0.65

0.7

0.75

0.8

0.85

0.9

0.95

1

010100

See paper for more resultsDifferent PTB dep. conversions

Page 23: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

24

Unsupervised Projection

German Spanish0

0.1

0.2

0.3

0.4

0.5

0.6

0.7

0.8

Mod. Prev.Mod. NextMonolingual EMHard proj.Hard proj. w/EMQG w/EM

Page 24: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

25

Supervised Projection

10 100 10000.58

0.63

0.68

0.73

0.78

0.83

0.88

Target onlySource textGold alignmentsGold parsesGold parses, alignments

Page 25: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

26

Conclusions

• Unified adaptation and projection• Conditional and generative training with

quasi-synchronous grammar features• Learned regular divergences• Ongoing work:– Joint, but not synchronous, inference– Better alignments– More adaptation problems

Page 26: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

27

QUESTIONS?Thanks!

Page 27: Parser Adaptation and Projection  with Quasi-Synchronous Grammar Features

28

Really Different Domains

中国 在 基本 建设 方面 , 开始

In the area of infrastructure construction , China has begun…