towards syntactically constrained statistical word alignment greg hanneman 11-734: advanced machine...

Towards Syntactically Towards Syntactically Constrained Statistical Constrained Statistical

Word AlignmentWord Alignment

Greg HannemanGreg Hanneman

11-734: Advanced Machine Translation SeminarApril 30, 2008

Outline• The word alignment problem• Base approaches• Syntax-based approaches

– Distortion models– Tree-to-string models– Tree-to-tree models

• Discussion

Word Alignment• Parallel sentence pair: F and E• Most general: map a subset of F to a

subset of E

Word Alignment• Very large alignment spaces!

– An n-word parallel sentence has n2 possible links and 2n2 possible alignments

– Restrict to one-to-one alignments: n! possible alignments

• Alignment models try to restrict or learn a probability distribution over this space to get the “best” alignment of a sentence

Outline• The word alignment problem• Base approaches• Syntax-based approaches

– Distortion models– Tree-to-string models– Tree-to-tree models

• Discussion

A Generative Story[Brown et al. 1990]

The proposal will not be implementedEnglish sentence

Fertility

Les propositions neseront pas applicationmises en

Lexical generation

Les propositions ne seront pas applicationmises en

Distortion

The Framework• F: words f1 … fj … fn

• E: words e1 … ei … em

• Compute P(F, A | E) for hidden alignment variable A: a1 … aj … an

– The major step: decomposition, model parameters, EM algorithm, etc.

• aj = i: word fj is aligned to word ei

The IBM Models[Brown et al. 1993; Och and Ney 2003]

• Model 1: “Bag of words” — word order doesn’t affect alignment

• Model 2: Position of words being aligned does matter

The IBM Models[Brown et al. 1993; Och and Ney 2003]

• Later models use more implicit structural or linguistic information, but not really syntax, and not really overtly– Fertility: P(φ | ei) of ei producing φ words in F– Distortion: P(τ, π | E) for a set of F words τ in

a permutation π – Previous alignments: Probs. for positions in F

of the different words of a fertile ei

The HMM Model[Vogel et al. 1996; Och and Ney 2003]

• Linguistic intuition: words, and their alignments, tend to clump together in clusters

• aj depends on absolute size of “jump” between it and aj–1

Discriminative Training• Consider all possible alignments, score

them, and pick the best ones under some set of constraints

• Can incorporate arbitrary features; generative models more fixed

• Generative models’ EM requires lots of unlabeled training data; discriminative requires some labeled data

Discriminative Alignment[Taskar et al. 2005]

• – Co-occurrence– Position difference– Co-occurrence of

following words– Word-frequency rank– Model 4 prediction– …

The

proposal

will

not

be

implemented

Les

propositions

ne

seront

pas

application

mises

en

),(),( jiT

ji fefev fw

Outline• The word alignment problem• Base approaches• Syntax-based approaches

– Distortion models– Tree-to-string models– Tree-to-tree models

• Discussion

Syntax-Based Approaches

• Constrain alignment space by looking beyond flat text stream: take higher-level sentence structure into account

• Representations– Constituency structure– Inversion Transduction Grammar– Dependency structure

An MT Motivation

Syntax-Based Distortion[DeNero and Klein 2007]

• Syntax-based MT should start from syntax-aware word alignments

• HMM model + target-language parse trees: prefer alignments that respect tree

• Handled in distortion model: jumps should reflect tree structure

Syntax-Based Distortion[DeNero and Klein 2007]

• HMM distortion: size of jump between aj–1 and aj

• Syntactic distortion: tree path between aj–

1 and aj

Syntax-Based Distortion[DeNero and Klein 2007]

• Training:100,000 parallel French–English and Chinese–English sentences with English parse trees

• Both E→F and F → E; combined with different unions and intersections, plus thresholds

• Test: Hand-aligned Hansards and NIST MT 2002 data

Syntax-Based Distortion[DeNero and Klein 2007]

• HMMs roughly equal, better than GIZA++

• Soft union for French; hard union for Chinese; competitive thresholding

Tree-to-String Models

Tree-to-String Models• New generative story• Word-level fertility and distortion

replaced with node insertion and sibling reordering

• Lexical translation still the same• Word alignment produced as a side

effect from lexical translations

Tree-to-String Alignment[Yamada and Knight 2001]

• Discussed in other sessions this semester• Training: 2121 short Japanese–English

sentences, modified Collins parser output for English

• Test: First 50 sentences of training corpus• Beat IBM Model 5 on human judgements;

perplexity between Model 1 and Model 5

Subtree Cloning[Gildea 2003]

• Original tree-to-string model is too strict– Syntactic divergences, reordering

• Soft constraint: allow alignments that violate tree structure, but at a cost– Tweak the tree side of the alignment to

contain things needed for the string side– Ex.: SVO to OSV

Subtree Cloning[Gildea 2003]

S

VP

AUX VP

do ADVP VB

RB

entirely

understand

NP

I

PRP

NP

PRP$ NN

your language

NP

I

PRP

Subtree Cloning[Gildea 2003]

S

VP

AUX VP

do

NP

I

PRP

ADVP VB

RB

entirely

understand

NP

PRP$ NN

your language

NP

I

PRP

Subtree Cloning[Gildea 2003]

S

VP

AUX VP

do

NP

I

PRP

ADVP VB

RB

entirely

understand

NP

PRP$ NN

your language

NP

I

PRP

men ti

NULL NULL

ni hua wo tu

tung

Subtree Cloning[Gildea 2003]

• For a node np:– Probability of cloning something as a

new child of np: single EM-learned constant for all np

– Probability of making that clone a node nc: uniform over all nc

• Surprising that this works…

Subtree Cloning[Gildea 2003]

• Compared with IBM 1–3, basic tree-to-string, basic tree-to-tree models

• Training: 4982 Korean–English sentence pairs, with manual Korean parse trees

• Test: 101 hand-aligned held-out sentences

Subtree Cloning[Gildea 2003]

• Cloning helps: as good or better than IBM

• Tree-to-tree model runs faster

Tree-to-Tree Models• Alignment must conform to tree

structure on both sides — space is more constrained

• Requires more transformation operations to handle divergent structures [Gildea 2003]

• Or we could be more permissive…

Inversion Transduction Grammar

[Wu 1997]• For bilingual

parsing; get one-to-one word alignment as a side effect

• Parallelbinary-branchingtrees with reordering

ITG Operations• A → [A A]

– Produce “A1 A2” in source and target streams• A → <A A>

– Produce “A1 A2” in source stream, “A2 A1” in target stream

• A → e / f– Produce “e” in source stream, “f” in target

stream

ITG Operations• “Canonical form” ITG produces only

one derivation for a given alignment– S → A | B | C– A → [A B] | [B B] | [C B] |

[A C] | [B C] | [C C]– B → <A A> | <B A> | <C A> |

<A C> | <B C> | <C C>– C → e / f

Alignment with ITG[Zhang and Gildea 2004]

• Compared IBM 1, IBM 4, ITG, and tree-to-string (with and without cloning)

• Training: Chinese–English (18,773) and French–English (20,000) sentences less than 25 words long

• Test: Hand-aligned Chinese–English (48) and French–English (447)

Alignment with ITG[Zhang and Gildea 2004]

• ITG best, or at least as good as IBM or tree-to-string plus cloning

• ITG has no linguistic syntax…

Dependency Parsing• Discussed in other sessions this

semester• Notion of violating “phrasal cohesion”

– Usually bad, but not always

Dependencies + ITG[Cherry and Lin 2006]

• Find invalid dependency spans; assign score of –∞ if used by the ITG parser

• Simple model: maximize co-occurrence score with penalty for distant words

• ITG reduces AER by 13% relative; dependencies + ITG reduce by 34%

nj

mi

jiji feφfev 52 10),(),(

Dependencies + ITG[Cherry and Lin 2006]

• Discriminative training with an SVM• Feature vector for each ITG rule

instance– Features from Taskar et al. [2005]– Feature marking ITG inversion rules– Feature (penalty) marking invalid spans

based on dependency tree

Dependencies + ITG[Cherry and Lin 2006]

• Compared Taskar et al. to D-ITG with hard and soft constraints

• Training: 50,000 French–English sentence pairs for counts and probabilities; 100 hand-annotated pairs with derived ITG trees for discriminative training

• Test: 347 hand-annotated sentences from 2003 parallel text workshop

Dependencies + ITG[Cherry and Lin 2006]

• Relative improvement smaller in discriminative training scenario with stronger objective function

• Hard constraint starts to hurt recall

Outline• The word alignment problem• Base approaches• Syntax-based approaches

– Distortion models– Tree-to-string models– Tree-to-tree models

• Discussion

All These Tradeoffs…• Mathematical and statistical

correctness vs. computability• Simple model vs. capturing linguistic

phenomena• Not enough syntactic information vs.

too much syntactic information• Ruling out bad alignments vs.

keeping good alignments around

• Completely unconstrained: every alignment link (ei, fj) either “on” or “off”

• Permutation space: one-to-one alignment with reordering [Taskar et al. 2005]

• ITG space: permutation space satisfying binary tree constraint [Wu 1997]

• Dependency space: permutation space maintaining phrasal cohesion

Alignment Spaces

Alignment Spaces• D-ITG space: Dependency ∩ ITG

space [Cherry and Lin 2006]

• HD-ITG space: D-ITG space where each span must contain a head [Cherry and Lin 2006a]

Examining Alignment Spaces

[Cherry and Lin 2006a]• Alignment score

– Learned co-occurrence score

– Gold-standard oracle score

Examining Alignment Spaces

[Cherry and Lin 2006a]• Learned co-occurrence score

– More restricted spaces give better results

Examining Alignment Spaces

[Cherry and Lin 2006a]• Oracle score: subsets of permutation

space– ITG rules out almost nothing correct– Beam search in dependency space does

worst

Conclusions• Base alignment models are

mathematical, limited notions of sentence structure

• Syntax-aware alignment helpful for syntax-aware MT [DeNero and Klein 2007]

• Using structure as a hard constraint is harmful for divergent sentences; tweaking trees [Gildea 2003] or using soft constraints [Cherry and Lin 2006] helps fix this

Conclusions• Surprise winner: ITG

– Computationally straightforward– Permissive, simple grammar that mostly only

rules out bad alignments [Cherry and Lin 2006a]

– Does a lot, even when it’s not the best• Discriminative framework looks

promising and flexible — can incorporate generative models as features [Taskar et al. 2005]

Towards the Future• Easy-to-run GIZA++ made

complicated IBM models the norm — promising discriminative or syntax-based models currently lack such a toolkit

• Syntax-based discriminative techniques — morphology, POS, semantic information…

• Any other ideas?

References• Brown, P., J. Cocke, S. Della Pietra, V. Della Pietra, F. Jelinek, J. Lafferty, R.

Mercer, and P. Roossin, “A statistical approach to machine translation,” Computational Linguistics, 16(2):79-85, 1990.

• Brown, P., S. Della Pietra, V. Della Pietra, and R. Mercer, “The mathematics of statistical machine translation: Parameter estimation,” Computational Linguistics, 19(2):263-311.

• Cherry, Colin and Dekang Lin, “Soft syntactic constraints for word alignment through discriminative training,” Proceedings of the COLING/ACL Poster Session, 105-112, 2006.

• Cherry, Colin and Dekang Lin, “A comparison of syntactically motivated alignment spaces,” Proceedings of EACL, 145-152, 2006a.

• DeNero, John and Dan Klein, “Tailoring word alignments to syntactic machine translation,” Proceedings of ACL, 17-24, 2007.

• Gildea, Daniel, “Loosely tree-based alignment for machine translation,” Proceedings of ACL, 80-87, 2003.

References• Och, Franz and Hermann Ney, “A systematic comparison of various

statistical alignment models,” Computational Linguistics, 29(1):19-51, 2003.

• Taskar, B., S. Lacoste-Julien, and D. Klein, “A discriminative matching approach to word alignment,” Proceedings of HLT/EMNLP, 73-80, 2005.

• Vogel, S., H. Ney, and C. Tillmann, “HMM-based word alignment in statistical translation,” Proceedings of COLING, 836-841, 1996.

• Wu, Dekai, “Stochastic inversion transduction grammars and bilingual parsing of parallel corpora,” Computational Linguistics, 23(3):377-403.

• Yamada, Kenji and Kevin Knight, “A syntax-based statistical translation model,” Proceedings of ACL, 523-530, 2001.

• Zhang, Hao and Daniel Gildea, “Syntax-based alignment: Supervised or unsupervised?” Proceedings of COLING, 418-424, 2004.