Alon Lavie Language Technologies Institute Carnegie Mellon University Joint work with Erik Peterson Alok Parlikar Vamshi Ambati Abhaya Agarwal Greg Hanneman Kevin Gimpel Edmund Huber March 28 2008 ID: 760713
Download Presentation The PPT/PDF document "Stat-XFER: A General Framework for Sear..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Stat-XFER: A General Framework for Search-based Syntax-driven MT
Alon Lavie
Language Technologies Institute
Carnegie Mellon University
Joint work with:
Erik Peterson, Alok Parlikar, Vamshi Ambati, Abhaya Agarwal, Greg Hanneman, Kevin Gimpel, Edmund Huber
Slide2March 28, 2008
NIST MT-08: CMU Stat-XFER
2
Outline
Context and Rationale
CMU Statistical Transfer MT Framework
Automatic Acquisition of Syntax-based MT Resources
Chinese-to-English System
Urdu-to-English System
Open Research Challenges
Conclusions
Slide3March 28, 2008
NIST MT-08: CMU Stat-XFER
3
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
Slide4Research Goals
Long-term research agenda (since 2000) focused on developing a unified framework for MT that addresses the core fundamental weaknesses of previous approaches:Representation – explore richer formalisms that can capture complex divergences between languagesAbility to handle morphologically complex languagesMethods for automatically acquiring MT resources from available data and combining them with manual resourcesAbility to address both rich and poor resource scenariosFocus has been on low-resource scenarios, scaling up to resource-rich scenarios in the past yearMain research funding sources: NSF (AVENUE and LETRAS projects) and DARPA (GALE)
March 28, 2008
4
NIST MT-08: CMU Stat-XFER
Slide5March 28, 2008
NIST MT-08: CMU Stat-XFER
5
CMU Statistical Transfer (Stat-XFER) MT Approach
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 syntactic-phrase correspondences can be
automatically acquired from parallel text
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
Slide6March 28, 2008
NIST MT-08: CMU Stat-XFER
6
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
Slide7Transfer 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
Slide8March 28, 2008
NIST MT-08: CMU Stat-XFER
8
Transfer Rule Formalism
Type informationPart-of-speech/constituent informationAlignmentsx-side constraintsy-side constraintsxy-constraints, e.g. ((Y1 AGR) = (X1 AGR))
;SL: the old man, TL: ha-ish ha-zaqenNP::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)))
Slide9March 28, 2008
NIST MT-08: CMU Stat-XFER
9
Translation Lexicon: Examples
PRO::PRO |: ["ANI"] -> ["I"]((X1::Y1)((X0 per) = 1)((X0 num) = s)((X0 case) = nom))PRO::PRO |: ["ATH"] -> ["you"]((X1::Y1)((X0 per) = 2)((X0 num) = s)((X0 gen) = m)((X0 case) = nom))
N::N |: ["$&H"] -> ["HOUR"]
(
(X1::Y1)
((X0 NUM) = s)
((Y0 NUM) = s)
((Y0 lex) = "HOUR")
)
N::N |: ["$&H"] -> ["hours"]
(
(X1::Y1)
((Y0 NUM) = p)
((X0 NUM) = p)
((Y0 lex) = "HOUR")
)
Slide10March 28, 2008
NIST MT-08: CMU Stat-XFER
10
Hebrew Transfer GrammarExample Rules
{NP1,2};;SL: $MLH ADWMH;;TL: A RED DRESSNP1::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)
)
Slide11March 28, 2008
NIST MT-08: CMU Stat-XFER
11
The Transfer 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
Slide12March 28, 2008
NIST MT-08: CMU Stat-XFER
12
The Transfer Engine
Some Unique Features:
Works with either learned or manually-developed transfer grammars
Handles rules with or without unification constraints
Supports interfacing with servers for morphological analysis and generation
Can handle ambiguous source-word analyses and/or SL segmentations represented in the form of lattice structures
Slide13March 28, 2008
NIST MT-08: CMU Stat-XFER
13
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')) ) ) ) ")
Slide14March 28, 2008
NIST MT-08: CMU Stat-XFER
14
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 features, with weights trained using Minimum Error Rate Training (MERT)
Scoring components:
Statistical Language Model
Rule Scores (currently: freq-based relative likelihood)
Lexical Probabilities
Fragmentation: how many arcs to cover the entire translation?
Length Penalty: how far from expected target length?
Slide15March 28, 2008
NIST MT-08: CMU Stat-XFER
15
XFER Lattice Decoder
0 0 ON THE FOURTH DAY THE LION ATE THE RABBIT TO A MORNING MEAL
Overall: -8.18323, Prob: -94.382, Rules: 0, Frag: 0.153846, Length: 0,
Words: 13,13
235 < 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')))))))>
Slide16March 28, 2008
NIST MT-08: CMU Stat-XFER
16
Stat-XFER MT Systems
General Stat-XFER framework under development for past seven years
Systems so far:
Chinese-to-English
Hebrew-to-English
Urdu-to-English
Hindi-to-English
Dutch-to-English
Mapudungun-to-Spanish
In progress or planned:
Arabic-to-English
Brazilian Portuguese-to-English
Native-Brazilian languages to Brazilian Portuguese
Hebrew-to-Arabic
Quechua-to-Spanish
Turkish-to-English
Slide17MT Resource Acquisition in Resource-rich Scenarios
Scenario: Significant amounts of parallel-text at sentence-level are availableParallel sentences can be word-aligned and parsed (at least on one side, ideally on both sides)Goal: Acquire syntax-based broad-coverage translation lexicons and transfer rule grammars automatically from the dataSyntax-based translation lexicons:Broad-coverage constituent-level translation equivalents at all levels of granularityCan serve as the elementary building blocks for transfer trees constructed at runtime using the transfer rules
March 28, 2008
17
NIST MT-08: CMU Stat-XFER
Slide18Acquisition Process
Automatic Process for Extracting Syntax-driven Rules and Lexicons from sentence-parallel data:Word-align the parallel corpus (GIZA++)Parse the sentences independently for both languagesRun our new PFA Constituent Aligner over the parsed sentence pairsExtract all aligned constituents from the parallel treesExtract all derived synchronous transfer rules from the constituent-aligned parallel treesConstruct a “data-base” of all extracted parallel constituents and synchronous rules with their frequencies and model them statistically (assign them relative-likelihood probabilities)
March 28, 2008
18
NIST MT-08: CMU Stat-XFER
Slide19PFA Constituent Node Aligner
Input: a bilingual pair of parsed and word-aligned sentencesGoal: find all sub-sentential constituent alignments between the two trees which are translation equivalents of each otherEquivalence Constraint: a pair of constituents <S,T> are considered translation equivalents if:All words in yield of <S> are aligned only to words in yield of <T> (and vice-versa)If <S> has a sub-constituent <S1> that is aligned to <T1>, then <T1> must be a sub-constituent of <T> (and vice-versa) Algorithm is a bottom-up process starting from word-level, marking nodes that satisfy the constraints
March 28, 2008
19
NIST MT-08: CMU Stat-XFER
Slide20PFA Node Alignment Algorithm Example
Words don’t have to align one-to-one
Constituent labels can be different in each languageTree Structures can be highly divergent
March 28, 2008
20
NIST MT-08: CMU Stat-XFER
Slide21PFA Node Alignment Algorithm Example
Aligner uses a clever arithmetic manipulation to enforce equivalence constraints
Resulting aligned nodes are highlighted in figure
March 28, 2008
21
NIST MT-08: CMU Stat-XFER
Slide22PFA Node Alignment Algorithm Example
Extraction of Phrases:
Get the Yields of the aligned nodes and add them to a phrase table tagged with syntactic categories on both source and target sidesExample:NP # NP :: 澳洲 # Australia
March 28, 2008
22
NIST MT-08: CMU Stat-XFER
Slide23PFA Node Alignment Algorithm Example
All Phrases from this tree pair:IP # S :: 澳洲 是 与 北韩 有 邦交 的 少数 国家 之一 。 # Australia is one of the few countries that have diplomatic relations with North Korea .VP # VP :: 是 与 北韩 有 邦交 的 少数 国家 之一 # is one of the few countries that have diplomatic relations with North KoreaNP # NP :: 与 北韩 有 邦交 的 少数 国家 之一 # one of the few countries that have diplomatic relations with North KoreaVP # VP :: 与 北韩 有 邦交 # have diplomatic relations with North KoreaNP # NP :: 邦交 # diplomatic relationsNP # NP :: 北韩 # North KoreaNP # NP :: 澳洲 # Australia
Slide24PFA Constituent Node Alignment Performance
Evaluation Data: Chinese-English TreebankParallel Chinese-English Treebank with manual word-alignments3342 Sentence PairsCreated a “Gold Standard” constituent alignments using the manual word-alignments and treebank treesNode Alignments: 39874 (About 12/tree pair)NP to NP Alignments: 5427Manual inspection confirmed that the constituent alignments are quite accurate (P > 0.80, R > 0.70)Evaluation: Run PFA Aligner with automatic word alignments on same data and compare with the “gold Standard” alignments
March 28, 2008
24
NIST MT-08: CMU Stat-XFER
Slide25PFA Constituent Node Alignment Performance
Viterbi Combination PrecisionRecallF-MeasureIntersection0.63820.53950.5847Union0.81140.29150.4289Sym-1 (Thot Toolkit)0.71420.45340.5547Sym-2 (Thot Toolkit)0.71350.46310.5617Grow-Diag-Final0.77770.34620.4791Grow-Diag-Final-and0.69880.47000.5620
Viterbi word alignments from Chinese-English and reverse directions were merged using different algorithmsTested the performance of Node-Alignment with each resulting alignment
March 28, 2008
25
NIST MT-08: CMU Stat-XFER
Slide26Transfer Rule Learning
Input: Constituent-aligned parallel treesIdea: Aligned nodes act as possible decomposition points of the parallel treesThe sub-trees of any aligned pair of nodes can be further decomposed at lower-level aligned nodes, creating an inventory of synchronous “TIG” correspondencesWe decompose only at the “highest” level possibleSynchronous “TIGs” can be converted into synchronous rulesAlgorithm: Find and extract all possible synchronous TIG decompositions from the node aligned trees“Flatten” the TIGs into synchronous CFG rules
March 28, 2008
26
NIST MT-08: CMU Stat-XFER
Slide27Rule Extraction
Algorithm
Flat Rule Creation:Sample rule:NP::NP [VP 北 CD 有 邦交 ] -> [one of the CD countries that VP](;; Alignments(X1::Y7)(X3::Y4))Note: Any one-to-one aligned words are elevated to Part-Of-Speech in flat rule. Any non-aligned words on either source or target side remain lexicalized
27
Slide28Rule Extraction Algorithm
All rules extracted: VP::VP [VC NP] -> [VBZ NP]((*score* 0.5);; Alignments(X1::Y1)(X2::Y2))VP::VP [VC NP] -> [VBZ NP]((*score* 0.5);; Alignments(X1::Y1)(X2::Y2))NP::NP [NR] -> [NNP]((*score* 0.5);; Alignments(X1::Y1)(X2::Y2))VP::VP [北 NP VE NP] -> [ VBP NP with NP]((*score* 0.5);; Alignments(X2::Y4)(X3::Y1)(X4::Y2))
All rules extracted: NP::NP [VP 北 CD 有 邦交 ] -> [one of the CD countries that VP]((*score* 0.5);; Alignments(X1::Y7)(X3::Y4))IP::S [ NP VP ] -> [NP VP ]((*score* 0.5);; Alignments(X1::Y1)(X2::Y2))NP::NP [ “北韩”] -> [“North” “Korea”](;Many to one alignment is a phrase)
28
Slide29Chinese-English System
Developed over past year under DARPA/GALE funding (within IBM-led “Rosetta” team)Participated in recent NIST MT-08 EvaluationLarge-scale broad-coverage systemIntegrates large manual resources with automatically extracted resourcesCurrent performance-level is still inferior to state-of-the-art phrase-based systems
March 28, 2008
29
NIST MT-08: CMU Stat-XFER
Slide30Chinese-English System
Lexical Resources:Manual Lexicons (base forms): LDC, ADSO, WikiTotal number of entries: 1.07 millionAutomatically acquired from parallel data:Approx 5 million sentences LDC/GALE dataFiltered down to phrases < 10 words in lengthFull formedTotal number of entries: 2.67 million
March 28, 2008
30
NIST MT-08: CMU Stat-XFER
Slide31Chinese-English System
Transfer Rules:61 manually developed transfer rulesHigh-accuracy rules extracted from manually word-aligned parallel data
CorpusSize (sens)Rules with StructureRules (count>=2)Complete Lexical rulesParallel Treebank (3K)3,34345,2661,96211,521993 sentences99312,6613312,199Parallel Treebank (7K)6,54141,9981,75616,081Merged Corpus set10K94,117316029,340
March 28, 2008
31
NIST MT-08: CMU Stat-XFER
Slide32March 28, 2008
NIST MT-08: CMU Stat-XFER
32
Translation Example
SrcSent 3 澳洲是与北韩有邦交的少数国家之一。
Gloss:
Australia is with north korea have diplomatic relations DE few country world
Reference:
Australia is one of the few countries that have diplomatic relations with North Korea.
Translation:
Australia is one of the few countries that has diplomatic relations with north korea .
Overall: -5.77439, Prob: -2.58631, Rules: -0.66874, TransSGT: -2.58646, TransTGS: -1.52858, Frag: -0.0413927, Length: -0.127525, Words: 11,15
( 0 10 "Australia is one of the few countries that has diplomatic relations with north korea" -5.66505 "澳洲 是 与 北韩 有 邦交 的 少数 国家 之一 " "(S1,1124731 (S,1157857 (NP,2 (NB,1 (LDC_N,1267 'Australia') ) ) (VP,1046077 (MISC_V,1 'is') (NP,1077875 (LITERAL 'one') (LITERAL 'of') (NP,1045537 (NP,1017929 (NP,1 (LITERAL 'the') (NUMNB,2 (LDC_NUM,420 'few') (NB,1 (WIKI_N,62230 'countries') ) ) ) (LITERAL 'that') (VP,1021811 (LITERAL 'has') (FBIS_NP,11916 'diplomatic relations') ) ) (FBIS_PP,84791 'with north korea') ) ) ) ) ) ")
( 10 11 "." -11.9549 "。" "(MISC_PUNC,20 '.')")
Slide33March 28, 2008
NIST MT-08: CMU Stat-XFER
33
Example: Syntactic Lexical Phrases
(LDC_N,1267 'Australia')
(WIKI_N,62230 'countries')
(FBIS_NP,11916 'diplomatic relations')
(FBIS_PP,84791 'with north korea')
Slide34March 28, 2008
NIST MT-08: CMU Stat-XFER
34
Example: Learned XFER Rules
;;SL::(2,4) 对 台 贸易
;;TL::(3,5) trade to taiwan
;;Score::22
{NP,1045537}
NP::NP [PP NP ] -> [NP PP ]
((*score* 0.916666666666667)
(X2::Y1)
(X1::Y2))
;;SL::(2,7) 直接 提到 伟 哥 的 广告
;;TL::(1,7) commercials that directly mention the name viagra
;;Score::5
{NP,1017929}
NP::NP [VP "的" NP ] -> [NP "that" VP ]
((*score* 0.111111111111111)
(X3::Y1)
(X1::Y3))
;;SL::(4,14) 有 一 至 多 个 高 新 技术 项目 或 产品
;;TL::(3,14) has one or more new , high level technology projects or products
;;Score::4
{VP,1021811}
VP::VP ["有" NP ] -> ["has" NP ]
((*score* 0.1)
(X2::Y2))
Slide35Current Performance
BLEUMETEORMT-03 (Dev-test)0.22270.4998MT-06 (Dev-test)0.20830.4713MT-08 (Test)0.13090.4614
March 28, 2008
NIST MT-08: CMU Stat-XFER
35
Slide36Urdu-to-English System
Primary condition did not allow parsing of parallel data low-resource scenario:Lexical resources: used provided LDC lexicon (tagged with POS), plus lexical entries acquired from word-aligning parallel-dataXFER rules: manually developed (48 rules)Language Model built from English side of parallel dataPrimary and Contrastive systems:Cont-1: Built a phrase-based system using MosesPrimary: Used our multi-engine MT system to combine our XFER system with our Moses systemCont-2: Our constrained Stat-XFER system onlyCont-3: Unconstrained version of Stat-XFER with just a large LMCont-4: MEMT of Stat-XFER (Cont-2) and Columbia’s constrained phrase-based systemCont-5: similar to Cont-4, but with unconstrained systems
March 28, 2008
NIST MT-08: CMU Stat-XFER
36
Slide37Urdu-to-English System
Our official reported scores are incorrect due to a “one-off” bug half way through our outputCorrected scores, as reported by NIST
March 28, 2008
NIST MT-08: CMU Stat-XFER
37
IBM BLEU
METEOR
Primary: MEMT (XFER+Moses)
0.1500
0.5087
Cont-1: Moses only
0.1820
0.5069
Cont-2: Stat-XFER only
0.1158
0.4528
Cont-3: Stat-XFER unconstrained
0.1443
0.4740
Cont-4: MEMT (XFER+Columbia)
0.1526
0.5142
Cont-5: MEMT (XFER+CU unconst)
0.1623
0.5127
Slide38Open Research Questions
Our large-scale Chinese-English system is still significantly behind phrase-based SMT. Why?Feature set is not sufficiently discriminant?Problems with the parsers for the two sides?Weaker decoder?Syntactic constituents don’t provide sufficient coverage?Bugs and deficiencies in the underlying algorithms?The ISI experience indicates that it may take a couple of years to catch up with and surpass the phrase-based systemsSignificant engineering issues to improve speed and efficient runtime processing and improved search
March 28, 2008
38
NIST MT-08: CMU Stat-XFER
Slide39Open Research Questions
Immediate Research Issues:Rule Learning:Study effects of learning rules from manually vs automatically word aligned dataStudy effects of parser accuracy on learned rulesEffective discriminant methods for modeling rule scoresRule filtering strategiesSyntax-based LMs: Our translations come out with a syntax-tree attached to themAdd a syntax-based LM feature that can discriminate between good and bad trees
March 28, 2008
39
NIST MT-08: CMU Stat-XFER
Slide40Conclusions
Stat-XFER is a promising general MT framework, suitable to a variety of MT scenarios and languagesProvides a complete solution for building end-to-end MT systems from parallel data, akin to phrase-based SMT systems (training, tuning, runtime system)No open-source publicly available toolkits (yet), but we welcome further collaboration activitiesComplex but highly interesting set of open research issues
March 28, 2008
40
NIST MT-08: CMU Stat-XFER
Slide41March 28, 2008
NIST MT-08: CMU Stat-XFER
41
Questions?