Statistical XFER: Hybrid Statistical Rule-based Machine Translation Alon Lavie Language Technologies Institute Carnegie Mellon University Joint work with:

Statistical XFER:Hybrid Statistical Rule-based

Machine Translation

Alon LavieLanguage Technologies Institute

Carnegie Mellon University

Joint work with: Jaime Carbonell, Lori Levin, Bob Frederking, Erik Peterson, Christian Monson, Vamshi Ambati, Greg Hanneman, Kathrin Probst, Ariadna Font-Llitjos, Alison Alvarez, Roberto Aranovich

Aug 29, 2007 Statistical XFER MT 2

Outline• Background and Rationale • Stat-XFER Framework Overview• Elicitation• Learning Transfer Rules• Automatic Rule Refinement• Example Prototypes• Major Research Challenges


Progression of MT• Started with rule-based systems

– Very large expert human effort to construct language-specific resources (grammars, lexicons)

– High-quality MT extremely expensive only for handful of language pairs

• Along came EBMT and then Statistical MT…– Replaced human effort with extremely large volumes of

parallel text data– Less expensive, but still only feasible for a small number of

language pairs– We “traded” human labor with data

• Where does this take us in 5-10 years?– Large parallel corpora for maybe 25-50 language pairs

• What about all the other languages?• Is all this data (with very shallow representation of

language structure) really necessary?• Can we build MT approaches that learn deeper levels of

language structure and how they map from one language to another?


Rule-based vs. Statistical MT

• Traditional Rule-based MT:– Expressive and linguistically-rich formalisms capable of

describing complex mappings between the two languages– Accurate “clean” resources– Everything constructed manually by experts– Main challenge: obtaining broad coverage

• Phrase-based Statistical MT:– Learn word and phrase correspondences automatically

from large volumes of parallel data– Search-based “decoding” framework:

• Models propose many alternative translations• Effective search algorithms find the “best” translation

– Main challenge: obtaining high translation accuracy


Main Principles of Stat-XFER

• Integrate the major strengths of rule-based and statistical MT within a common framework:– Linguistically rich formalism that can express complex and

abstract compositional transfer rules– Rules can be written by human experts and also acquired

automatically from data– Easy integration of morphological analyzers and

generators– Word and basic phrase correspondences (i.e. base NPs)

can be automatically acquired from parallel text when available

– Search-based decoding from statistical MT adapted to find the best translation within the search space: multi-feature scoring, beam-search, parameter optimization, etc.

– Framework suitable for both resource-rich and resource-poor language scenarios


Stat-XFER MT Approach Interlingua

Syntactic Parsing

Semantic Analysis

Sentence Planning

Text Generation

Source (e.g. Quechua)

Target(e.g. English)

Transfer Rules

Direct: SMT, EBMT

Statistical-XFER


Transfer Engine

Language Model + Additional Features

Transfer Rules{NP1,3}NP1::NP1 [NP1 "H" ADJ] -> [ADJ NP1]((X3::Y1) (X1::Y2) ((X1 def) = +) ((X1 status) =c absolute) ((X1 num) = (X3 num)) ((X1 gen) = (X3 gen)) (X0 = X1))

Translation Lexicon

N::N |: ["$WR"] -> ["BULL"]((X1::Y1) ((X0 NUM) = s) ((Y0 lex) = "BULL"))

N::N |: ["$WRH"] -> ["LINE"]((X1::Y1) ((X0 NUM) = s) ((Y0 lex) = "LINE"))

Source Input

בשורה הבאה

Decoder

English Output

in the next line

Translation Output Lattice

(0 1 "IN" @PREP)(1 1 "THE" @DET)(2 2 "LINE" @N)(1 2 "THE LINE" @NP)(0 2 "IN LINE" @PP)(0 4 "IN THE NEXT LINE" @PP)

Preprocessing

Morphology


Transfer Rule Formalism

Type informationPart-of-speech/constituent

informationAlignments

x-side constraints

y-side constraints

xy-constraints, e.g. ((Y1 AGR) = (X1 AGR))

;SL: the old man, TL: ha-ish ha-zaqen

NP::NP [DET ADJ N] -> [DET N DET ADJ]((X1::Y1)(X1::Y3)(X2::Y4)(X3::Y2)

((X1 AGR) = *3-SING)((X1 DEF = *DEF)((X3 AGR) = *3-SING)((X3 COUNT) = +)

((Y1 DEF) = *DEF)((Y3 DEF) = *DEF)((Y2 AGR) = *3-SING)((Y2 GENDER) = (Y4 GENDER)))


Transfer Rule Formalism (II)

Value constraints

Agreement constraints

;SL: the old man, TL: ha-ish ha-zaqen

NP::NP [DET ADJ N] -> [DET N DET ADJ]((X1::Y1)(X1::Y3)(X2::Y4)(X3::Y2)

((X1 AGR) = *3-SING)((X1 DEF = *DEF)((X3 AGR) = *3-SING)((X3 COUNT) = +)

((Y1 DEF) = *DEF)((Y3 DEF) = *DEF)((Y2 AGR) = *3-SING)((Y2 GENDER) = (Y4 GENDER)))


Hebrew Manual Transfer Grammar (human-developed)

• Initially developed in a couple of days, with some later revisions by a CL post-doc

• Current grammar has 36 rules:– 21 NP rules – one PP rule – 6 verb complexes and VP rules – 8 higher-phrase and sentence-level rules

• Captures the most common (mostly local) structural differences between Hebrew and English


Hebrew Transfer GrammarExample Rules

{NP1,2};;SL: $MLH ADWMH;;TL: A RED DRESS

NP1::NP1 [NP1 ADJ] -> [ADJ NP1]((X2::Y1)(X1::Y2)((X1 def) = -)((X1 status) =c absolute)((X1 num) = (X2 num))((X1 gen) = (X2 gen))(X0 = X1))

{NP1,3};;SL: H $MLWT H ADWMWT;;TL: THE RED DRESSES

NP1::NP1 [NP1 "H" ADJ] -> [ADJ NP1]((X3::Y1)(X1::Y2)((X1 def) = +)((X1 status) =c absolute)((X1 num) = (X3 num))((X1 gen) = (X3 gen))(X0 = X1))


The XFER Engine

• Input: source-language input sentence, or source-language confusion network

• Output: lattice representing collection of translation fragments at all levels supported by transfer rules

• Basic Algorithm: “bottom-up” integrated “parsing-transfer-generation” guided by the transfer rules– Start with translations of individual words and phrases

from translation lexicon– Create translations of larger constituents by applying

applicable transfer rules to previously created lattice entries

– Beam-search controls the exponential combinatorics of the search-space, using multiple scoring features


Source-language Confusion Network Hebrew Example

• Input word: B$WRH

0 1 2 3 4 |--------B$WRH--------| |-----B-----|$WR|--H--| |--B--|-H--|--$WRH---|


XFER Output Lattice(28 28 "AND" -5.6988 "W" "(CONJ,0 'AND')")(29 29 "SINCE" -8.20817 "MAZ " "(ADVP,0 (ADV,5 'SINCE')) ")(29 29 "SINCE THEN" -12.0165 "MAZ " "(ADVP,0 (ADV,6 'SINCE THEN')) ")(29 29 "EVER SINCE" -12.5564 "MAZ " "(ADVP,0 (ADV,4 'EVER SINCE')) ")(30 30 "WORKED" -10.9913 "&BD " "(VERB,0 (V,11 'WORKED')) ")(30 30 "FUNCTIONED" -16.0023 "&BD " "(VERB,0 (V,10 'FUNCTIONED')) ")(30 30 "WORSHIPPED" -17.3393 "&BD " "(VERB,0 (V,12 'WORSHIPPED')) ")(30 30 "SERVED" -11.5161 "&BD " "(VERB,0 (V,14 'SERVED')) ")(30 30 "SLAVE" -13.9523 "&BD " "(NP0,0 (N,34 'SLAVE')) ")(30 30 "BONDSMAN" -18.0325 "&BD " "(NP0,0 (N,36 'BONDSMAN')) ")(30 30 "A SLAVE" -16.8671 "&BD " "(NP,1 (LITERAL 'A') (NP2,0 (NP1,0 (NP0,0 (N,34 'SLAVE')) ) ) ) ")(30 30 "A BONDSMAN" -21.0649 "&BD " "(NP,1 (LITERAL 'A') (NP2,0 (NP1,0 (NP0,0 (N,36 'BONDSMAN')) ) ) ) ")


The Lattice Decoder• Simple Stack Decoder, similar in principle to simple

Statistical MT decoders• Searches for best-scoring path of non-overlapping

lattice arcs• No reordering during decoding• Scoring based on log-linear combination of scoring

components, with weights trained using MERT• Scoring components:

– Statistical Language Model– Fragmentation: how many arcs to cover the entire

translation?– Length Penalty– Rule Scores– Lexical Probabilities


XFER Lattice Decoder0 0 ON THE FOURTH DAY THE LION ATE THE RABBIT TO A MORNING MEALOverall: -8.18323, Prob: -94.382, Rules: 0, Frag: 0.153846, Length: 0,

Words: 13,13235 < 0 8 -19.7602: B H IWM RBI&I (PP,0 (PREP,3 'ON')(NP,2 (LITERAL 'THE')

(NP2,0 (NP1,1 (ADJ,2 (QUANT,0 'FOURTH'))(NP1,0 (NP0,1 (N,6 'DAY')))))))>918 < 8 14 -46.2973: H ARIH AKL AT H $PN (S,2 (NP,2 (LITERAL 'THE') (NP2,0

(NP1,0 (NP0,1 (N,17 'LION')))))(VERB,0 (V,0 'ATE'))(NP,100 (NP,2 (LITERAL 'THE') (NP2,0 (NP1,0 (NP0,1 (N,24 'RABBIT')))))))>

584 < 14 17 -30.6607: L ARWXH BWQR (PP,0 (PREP,6 'TO')(NP,1 (LITERAL 'A') (NP2,0 (NP1,0 (NNP,3 (NP0,0 (N,32 'MORNING'))(NP0,0 (N,27 'MEAL')))))))>


Data Elicitation for Languages with Limited Resources

• Rationale:– Large volumes of parallel text not available create

a small maximally-diverse parallel corpus that directly supports the learning task

– Bilingual native informant(s) can translate and align a small pre-designed elicitation corpus, using elicitation tool

– Elicitation corpus designed to be typologically and structurally comprehensive and compositional

– Transfer-rule engine and new learning approach support acquisition of generalized transfer-rules from the data


Elicitation Tool: English-Chinese Example


Elicitation Tool:English-Chinese Example


Elicitation Tool:English-Hindi Example


Elicitation Tool:English-Arabic Example


Elicitation Tool:Spanish-Mapudungun Example


Designing Elicitation Corpora

• Goal: Create a small representative parallel corpus that contains examples of the most important translation correspondences and divergences between the two languages

• Method: – Elicit translations and word alignments for a broad diversity of

linguistic phenomena and constructions• Current Elicitation Corpus: ~3100 sentences and phrases,

constructed based on a broad feature-based specification• Open Research Issues:

– Feature Detection: discover what features exist in the language and where/how they are marked

• Example: does the language mark gender of nouns? How and where are these marked?

– Dynamic corpus navigation based on feature detection: no need to elicit for combinations involving non-existent features


Rule Learning - Overview

• Goal: Acquire Syntactic Transfer Rules• Use available knowledge from the source

side (grammatical structure)• Three steps:

1. Flat Seed Generation: first guesses at transfer rules; flat syntactic structure

2. Compositionality Learning: use previously learned rules to learn hierarchical structure

3. Constraint Learning: refine rules by learning appropriate feature constraints


Flat Seed Rule Generation

Learning Example: NP

Eng: the big apple

Heb: ha-tapuax ha-gadol

Generated Seed Rule:

NP::NP [ART ADJ N] [ART N ART ADJ]

((X1::Y1)

(X1::Y3)

(X2::Y4)

(X3::Y2))


Compositionality LearningInitial Flat Rules: S::S [ART ADJ N V ART N] [ART N ART ADJ V P ART N]

((X1::Y1) (X1::Y3) (X2::Y4) (X3::Y2) (X4::Y5) (X5::Y7) (X6::Y8))

NP::NP [ART ADJ N] [ART N ART ADJ]

((X1::Y1) (X1::Y3) (X2::Y4) (X3::Y2))

NP::NP [ART N] [ART N]

((X1::Y1) (X2::Y2))

Generated Compositional Rule:

S::S [NP V NP] [NP V P NP]

((X1::Y1) (X2::Y2) (X3::Y4))


Constraint LearningInput: Rules and their Example Sets

S::S [NP V NP] [NP V P NP] {ex1,ex12,ex17,ex26}

((X1::Y1) (X2::Y2) (X3::Y4))

NP::NP [ART ADJ N] [ART N ART ADJ] {ex2,ex3,ex13}

((X1::Y1) (X1::Y3) (X2::Y4) (X3::Y2))

NP::NP [ART N] [ART N] {ex4,ex5,ex6,ex8,ex10,ex11}

((X1::Y1) (X2::Y2))

Output: Rules with Feature Constraints:

S::S [NP V NP] [NP V P NP]

((X1::Y1) (X2::Y2) (X3::Y4)

(X1 NUM = X2 NUM)

(Y1 NUM = Y2 NUM)

(X1 NUM = Y1 NUM))


Automated Rule Refinement

• Bilingual informants can identify translation errors and pinpoint the errors

• A sophisticated trace of the translation path can identify likely sources for the error and do “Blame Assignment”

• Rule Refinement operators can be developed to modify the underlying translation grammar (and lexicon) based on characteristics of the error source:– Add or delete feature constraints from a rule– Bifurcate a rule into two rules (general and specific)– Add or correct lexical entries

• See [Font-Llitjos, Carbonell & Lavie, 2005]


Stat-XFER MT Prototypes • General Statistical XFER framework under development for

past five years (funded by NSF and DARPA)• Prototype systems so far:

– Chinese-to-English– Dutch-to-English– French-to-English– Hindi-to-English– Hebrew-to-English– Mapudungun-to-Spanish

• In progress or planned:– Brazilian Portuguese-to-English– Native-Brazilian languages to Brazilian Portuguese– Hebrew-to-Arabic– Iñupiaq-to-English– Urdu-to-English– Turkish-to-English


Chinese-English Stat-XFER System

• Bilingual lexicon: over 1.1 million entries (multiple resources, incl. ADSO, Wikipedia, extracted base NPs)

• Manual syntactic XFER grammar: 76 rules! (mostly NPs, a few PPs, and reordering of NPs/PPs within VPs)

• Multiple overlapping Chinese word segmentations• English morphology generation• Uses CMU SMT-group’s Suffix-Array LM toolkit for LM• Current Performance (GALE dev-test):

– NW: • XFER: 10.89(B)/0.4509(M)• Best (UMD): 15.58(B)/0.4769(M)

– NG • XFER: 8.92(B)/0.4229(M) • Best (UMD): 12.96(B)/0.4455(M)

• In Progress:– Automatic extraction of “clean” base NPs from parallel

data– Automatic learning and extraction of high-quality transfer-

rules from parallel data


Translation Example• REFERENCE: When responding to whether it is possible

to extend Russian fleet's stationing deadline at the Crimean peninsula, Yanukovych replied, "Without a doubt.

• Stat-XFER (0.3989): In reply to whether the possibility to extend the Russian fleet stationed in Crimea Pen. left the deadline of the problem , Yanukovich replied : " of course .

• IBM-ylee (0.2203): In response to the possibility to extend the deadline for the presence in Crimea peninsula , the Queen Vic said : " of course .

• CMU-SMT (0.2067): In response to a possible extension of the fleet in the Crimean Peninsula stay on the issue , Yanukovych vetch replied : " of course .

• maryland-hiero (0.1878): In response to the possibility of extending the mandate of the Crimean peninsula in , replied: "of course.

• IBM-smt (0.1862): The answer is likely to be extended the Crimean peninsula of the presence of the problem, Yanukovych said: " Of course.

• CMU-syntax (0.1639): In response to the possibility of extension of the presence in the Crimean Peninsula , replied : " of course .


Major Research Directions

• Automatic Transfer Rule Learning:– From manually word-aligned elicitation corpus– From large volumes of automatically word-aligned

“wild” parallel data– In the absence of morphology or POS annotated

lexica– Compositionality and generalization– Identifying “good” rules from “bad” rules– Effective models for rule scoring for

• Decoding: using scores at runtime• Pruning the large collections of learned rules

– Learning Unification Constraints



• Extraction of Base-NP translations from parallel data:– Base-NPs are extremely important “building blocks” for

transfer-based MT systems• Frequent, often align 1-to-1, improve coverage• Correctly identifying them greatly helps automatic word-

alignment of parallel sentences– Parsers (or NP-chunkers) available for both languages:

Extract base-NPs independently on both sides and find their correspondences

– Parsers (or NP-chunkers) available for only one language (i.e. English): Extract base-NPs on one side, and find reliable correspondences for them using word-alignment, frequency distributions, other features…

• Promising preliminary results



• Algorithms for XFER and Decoding– Integration and optimization of multiple

features into search-based XFER parser– Complexity and efficiency improvements

(i.e. “Cube Pruning”)– Non-monotonicity issues (LM scores,

unification constraints) and their consequences on search


Major Research Directions• Discriminative Language Modeling for MT:

– Current standard statistical LMs provide only weak discrimination between good and bad translation hypotheses

– New Idea: Use “occurrence-based” statistics:• Extract instances of lexical, syntactic and semantic features

from each translation hypothesis• Determine whether these instances have been “seen before”

(at least once) in a large monolingual corpus– The Conjecture: more grammatical MT hypotheses are

likely to contain higher proportions of feature instances that have been seen in a corpus of grammatical sentences.

– Goals: • Find the set of features that provides the best discrimination

between good and bad translations• Learn how to combine these into a LM-like function for scoring

alternative MT hypotheses



• Building Elicitation Corpora:– Feature Detection– Corpus Navigation

• Automatic Rule Refinement• Translation for highly polysynthetic

languages such as Mapudungun and Iñupiaq


Questions?

Documents

Statistical XFER: Hybrid Statistical Rule-based Machine Translation Alon Lavie Language Technologies Institute Carnegie Mellon University Joint work with: