1. Machine Translation Overview
Alon Lavie
Language Technologies Institute
Carnegie Mellon University
LTI Open House
February 26, 2009

2. Machine Translation: History
MT started in 1940’s, one of the first conceived application of computers
Promising “toy” demonstrations in the 1950’s, failed miserably to scale up to “real” systems
AIPAC Report: MT recognized as an extremely difficult, “AI-complete” problem in the early 1960’s
MT Revival started in earnest in 1980s (US, Japan)
Field dominated by rule-based approaches, requiring 100s of K-years of manual development
Economic incentive for developing MT systems for small number of language pairs (mostly European languages)
February 26, 2009
LTI OH 2009

3. Machine Translation: Where are we today?
Age of Internet and Globalization – great demand for translation services and MT:
Multiple official languages of UN, EU, Canada, etc.
Documentation dissemination for large manufacturers (Microsoft, IBM, Caterpillar)
Language and translation services business sector estimated at $16 Billion worldwide in 2008
Economic incentive is still primarily within a small number of language pairs
Some fairly good commercial products in the market for these language pairs
Primarily a product of rule-based systems after many years of development
Web-based (mostly free) MT services: Google, Babelfish, others…
Pervasive MT between many language pairs still non-existent and not on the immediate horizon
February 26, 2009
LTI OH 2009

4. Representative Example: Google Translate
February 26, 2009
LTI OH 2009

5. Google Translate

6. Google Translate

7. Example of High Quality MT
PAHO’s Spanam system:
Mediante petición recibida por la Comisión Interamericana de Derechos Humanos (en adelante …) el 6 de octubre de 1997, el señor Lino César Oviedo (en adelante …) denunció que la República del Paraguay (en adelante …) violó en su perjuicio los derechos a las garantías judiciales … en su contra.
Through petition received by the `Inter-American Commission on Human Rights` (hereinafter …) on 6 October 1997, Mr. Linen César Oviedo (hereinafter “the petitioner”) denounced that the Republic of Paraguay (hereinafter …) violated to his detriment the rights to the judicial guarantees, to the political participation, to // equal protection and to the honor and dignity consecrated in articles 8, 23, 24 and 11, respectively, of the `American Convention on Human Rights` (hereinafter …”), as a consequence of judgments initiated against it.
February 26, 2009
LTI OH 2009

8. Core Challenges of MT Ambiguity and Language Divergences:
Human languages are highly ambiguous, and differently in different languages
Ambiguity at all “levels”: lexical, syntactic, semantic, language-specific constructions and idioms
Amount of required knowledge:
Translation equivalencies for vast vocabularies (several 100k words and phrases)
Syntactic knowledge (how to map syntax of one language to another), plus more complex language divergences (semantic differences, constructions and idioms, etc.)
How do you acquire and construct a knowledge base that big that is (even mostly) correct and consistent?
February 26, 2009
LTI OH 2009

9. Major Sources of Translation Problems
Lexical Differences:
Multiple possible translations for SL word, or difficulties expressing SL word meaning in a single TL word
Structural Differences:
Syntax of SL is different than syntax of the TL: word order, sentence and constituent structure
Differences in Mappings of Syntax to Semantics:
Meaning in TL is conveyed using a different syntactic structure than in the SL
Idioms and Constructions
February 26, 2009
LTI OH 2009

10. How to Tackle the Core Challenges
Manual Labor: 1000s of person-years of human experts developing large word and phrase translation lexicons and translation rules.
Example: Systran’s RBMT systems.
Lots of Parallel Data: data-driven approaches for finding word and phrase correspondences automatically from large amounts of sentence-aligned parallel texts. Example: Statistical MT systems.
Learning Approaches: learn translation rules automatically from small amounts of human translated and word-aligned data. Example: AVENUE’s Statistical XFER approach.
Simplify the Problem: build systems that are limited-domain or constrained in other ways. Examples: CATALYST, NESPOLE!.
February 26, 2009
LTI OH 2009

11. State-of-the-Art in MT
What users want:
General purpose (any text)
High quality (human level)
Fully automatic (no user intervention)
We can meet any 2 of these 3 goals today, but not all three at once:
FA HQ: Knowledge-Based MT (KBMT)
FA GP: Corpus-Based (Example-Based) MT
GP HQ: Human-in-the-loop (efficiency tool)
February 26, 2009
LTI OH 2009

12. Types of MT Applications:
Assimilation: multiple source languages, uncontrolled style/topic. General purpose MT, no semantic analysis. (GP FA or GP HQ)
Dissemination: one source language, controlled style, single topic/domain. Special purpose MT, full semantic analysis. (FA HQ)
Communication: Lower quality may be okay, but system robustness, real-time required.
February 26, 2009
LTI OH 2009

13. Approaches to MT: Vaquois MT Triangle
Interlingua
Give-information+personal-data (name=alon_lavie)
Generation
Analysis
Transfer
[s [vp accusative_pronoun “chiamare” proper_name]]
[s [np [possessive_pronoun “name”]]
[vp “be” proper_name]]
Direct
Mi chiamo Alon Lavie
My name is Alon Lavie
February 26, 2009
LTI OH 2009

14. Knowledge-based Interlingual MT
The classic “deep” Artificial Intelligence approach:
Analyze the source language into a detailed symbolic representation of its meaning
Generate this meaning in the target language
“Interlingua”: one single meaning representation for all languages
Nice in theory, but extremely difficult in practice:
What kind of representation?
What is the appropriate level of detail to represent?
How to ensure that the interlingua is in fact universal?
“Demonstration” is now set of KANT interlinguas
Downloaded here from AMTA interlingua workshop webpage: clicking on sentences show the IL
Note use of phrasal lexical units!
Start with #4: “simple” example (with a 2-level genl. quantifier!)
1: rel. clause
3: conj “but”, coordination, another genl. quant.
5: implicit rel. clause, apposition
6: “latter”/”former”
7: appositive VP
8: quote marks
13/14: complex [numbers different on frontpage and files!]
21/22: “all” is (:OR SINGULAR PLURAL) [ambiguity packing!]
February 26, 2009
LTI OH 2009

15. Interlingua versus Transfer
With interlingua, need only N parsers/ generators instead of N2 transfer systems: L2 L2 L3 L1 L3 L1
interlingua L6 L4 L6 L4 L5 L5
February 26, 2009
LTI OH 2009

16. Multi-Engine MT Apply several MT engines to each input in parallel
Create a combined translation from the individual translations
Goal is to combine strengths, and avoid weaknesses.
Along all dimensions: domain limits, quality, development time/cost, run-time speed, etc.
Various approaches to the problem
February 26, 2009
LTI OH 2009

17. Speech-to-Speech MT Speech just makes MT (much) more difficult:
Spoken language is messier
False starts, filled pauses, repetitions, out-of-vocabulary words
Lack of punctuation and explicit sentence boundaries
Current Speech technology is far from perfect
Need for speech recognition and synthesis in foreign languages
Robustness: MT quality degradation should be proportional to SR quality
Tight Integration: rather than separate sequential tasks, can SR + MT be integrated in ways that improves end-to-end performance?
February 26, 2009
LTI OH 2009

18. MT at the LTI
LTI originated as the Center for Machine Translation (CMT) in 1985
MT continues to be a prominent sub-discipline of research with the LTI
More MT faculty than any of the other areas
More MT faculty than anywhere else
Active research on all main approaches to MT: Interlingua, Transfer, EBMT, SMT
Leader in the area of speech-to-speech MT
Multi-Engine MT (MEMT)
MT Evaluation (METEOR)
February 26, 2009
LTI OH 2009

19. Phrase-based Statistical MT
Word-to-word and phrase-to-phrase translation pairs are acquired automatically from data and assigned probabilities based on a statistical model
Extracted and trained from very large amounts of sentence-aligned parallel text
Word alignment algorithms
Phrase detection algorithms
Translation model probability estimation
Main approach pursued in CMU systems in the DARPA/TIDES program and now in GALE
Chinese-to-English and Arabic-to-English
Most active work is on improved word alignment, phrase extraction and advanced decoding techniques
Contact Faculty: Stephan Vogel
February 26, 2009
LTI OH 2009

20. EBMT Developed originally for the PANGLOSS system in the early 1990s
Translation between English and Spanish
Generalized EBMT under development for the past several years
Used in a variety of projects in recent years
DARPA TIDES and GALE programs
DIPLOMAT and TONGUES
Active research work on improving alignment and indexing, decoding from a lattice
Contact Faculty: Ralf Brown and Jaime Carbonell
February 26, 2009
LTI OH 2009

21. CMU Statistical Transfer (Stat-XFER) MT Approach
Integrate the major strengths of rule-based and statistical MT within a common statistically-driven 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
Most active work on phrase and rule acquisition from parallel data, efficient decoding, joint decoding with non-syntactic phrases, MT for low-resource languages
Contact Faculty: Alon Lavie, Lori Levin, Bob Frederking and Jaime Carbonell
February 26, 2009
LTI OH 2009

22. Speech-to-Speech MT
Evolution from JANUS/C-STAR systems to NESPOLE!, LingWear, BABYLON, TRANSTAC
Early 1990s: first prototype system that fully performed sp-to-sp (very limited domains)
Interlingua-based, but with shallow task-oriented representations:
“we have single and double rooms available”
[give-information+availability]
(room-type={single, double})
Semantic Grammars for analysis and generation
Multiple languages: English, German, French, Italian, Japanese, Korean, and others
Phrase-based SMT applied in Speech-to-Speech scenarios
Most active work on portable speech translation on small devices: Iraqi-Arabic/English and Thai/English
Contact Faculty: Alan Black, Stephan Vogel, Florian Metze and Alex Waibel
February 26, 2009
LTI OH 2009

23. KBMT: KANT, KANTOO, CATALYST
Deep knowledge-based framework, with symbolic interlingua as intermediate representation
Syntactic and semantic analysis into a unambiguous detailed symbolic representation of meaning using unification grammars and transformation mappers
Generation into the target language using unification grammars and transformation mappers
First large-scale multi-lingual interlingua-based MT system deployed commercially:
CATALYST at Caterpillar: high quality translation of documentation manuals for heavy equipment
Limited domains and controlled English input
Minor amounts of post-editing
Active follow-on projects
Contact Faculty: Eric Nyberg and Teruko Mitamura
February 26, 2009
LTI OH 2009

24. Multi-Engine MT
New decoding-based approach developed in recent years under DoD and DARPA funding (used in GALE)
Main ideas:
Treat original engines as “black boxes”
Align the word and phrase correspondences between the translations
Build a collection of synthetic combinations based on the aligned words and phrases
Score the synthetic combinations based on Language Model and confidence measures
Select the top-scoring synthetic combination
Architecture Issues: integrating “workflows” that produce multiple translations and then combine them with MEMT
IBM’s UIMA architecture
Contact Faculty: Alon Lavie
February 26, 2009
LTI OH 2009

25. Automatic MT Evaluation
METEOR: new metric developed at CMU
Improves upon BLEU metric developed by IBM and used extensively in recent years
Main ideas:
Assess the similarity between a machine-produced translation and (several) human reference translations
Similarity is based on word-to-word matching that matches:
Identical words
Morphological variants of same word (stemming)
synonyms
Similarity is based on weighted combination of Precision and Recall
Address fluency/grammaticality via a direct penalty: how well-ordered is the matching of the MT output with the reference?
Improved levels of correlation with human judgments of MT Quality
Contact Faculty: Alon Lavie
February 26, 2009
LTI OH 2009

26. Summary
Main challenges for current state-of-the-art MT approaches - Coverage and Accuracy:
Acquiring broad-coverage high-accuracy translation lexicons (for words and phrases)
learning syntactic mappings between languages from parallel word-aligned data
overcoming syntax-to-semantics differences and dealing with constructions
Stronger Target Language Modeling
February 26, 2009
LTI OH 2009

27. Questions…
February 26, 2009
LTI OH 2009

28. Lexical Differences
SL word has several different meanings, that translate differently into TL
Ex: financial bank vs. river bank
Lexical Gaps: SL word reflects a unique meaning that cannot be expressed by a single word in TL
Ex: English snub doesn’t have a corresponding verb in French or German
TL has finer distinctions than SL  SL word should be translated differently in different contexts
Ex: English wall can be German wand (internal), mauer (external)
February 26, 2009
LTI OH 2009

29. Structural Differences
Syntax of SL is different than syntax of the TL:
Word order within constituents:
English NPs: art adj n the big boy
Hebrew NPs: art n art adj ha yeled ha gadol
Constituent structure:
English is SVO: Subj Verb Obj I saw the man
Modern Arabic is VSO: Verb Subj Obj
Different verb syntax:
Verb complexes in English vs. in German
I can eat the apple Ich kann den apfel essen
Case marking and free constituent order
German and other languages that mark case:
den apfel esse Ich the(acc) apple eat I(nom)
February 26, 2009
LTI OH 2009

30. Syntax-to-Semantics Differences
Meaning in TL is conveyed using a different syntactic structure than in the SL
Changes in verb and its arguments
Passive constructions
Motion verbs and state verbs
Case creation and case absorption
Main Distinction from Structural Differences:
Structural differences are mostly independent of lexical choices and their semantic meaning  can be addressed by transfer rules that are syntactic in nature
Syntax-to-semantic mapping differences are meaning-specific: require the presence of specific words (and meanings) in the SL
February 26, 2009
LTI OH 2009

31. Syntax-to-Semantics Differences
Structure-change example:
I like swimming
“Ich scwhimme gern”
I swim gladly
Verb-argument example:
Jones likes the film.
“Le film plait à Jones.”
(lit: “the film pleases to Jones”)
Passive Constructions
Example: French reflexive passives: Ces livres se lisent facilement *”These books read themselves easily” These books are easily read
February 26, 2009
LTI OH 2009

32. Idioms and Constructions
Main Distinction: meaning of whole is not directly compositional from meaning of its sub-parts  no compositional translation
Examples:
George is a bull in a china shop
He kicked the bucket
Can you please open the window?
February 26, 2009
LTI OH 2009

33. Formulaic Utterances Good night. tisbaH cala xEr waking up on good
Romanization of Arabic from CallHome Egypt
February 26, 2009
LTI OH 2009

34. Analysis and Generation Main Steps
Morphological analysis (word-level) and POS tagging
Syntactic analysis and disambiguation (produce syntactic parse-tree)
Semantic analysis and disambiguation (produce symbolic frames or logical form representation)
Map to language-independent Interlingua
Generation:
Generate semantic representation in TL
Sentence Planning: generate syntactic structure and lexical selections for concepts
Surface-form realization: generate correct forms of words
February 26, 2009
LTI OH 2009

35. Direct Approaches No intermediate stage in the translation
First MT systems developed in the 1950’s-60’s (assembly code programs)
Morphology, bi-lingual dictionary lookup, local reordering rules
“Word-for-word, with some local word-order adjustments”
Modern Approaches:
Phrase-based Statistical MT (SMT)
Example-based MT (EBMT)
February 26, 2009
LTI OH 2009

36. Statistical MT (SMT)
Proposed by IBM in early 1990s: a direct, purely statistical, model for MT
Most dominant approach in current MT research
Evolved from word-level translation to phrase-based translation
Main Ideas:
Training: statistical “models” of word and phrase translation equivalence are learned automatically from bilingual parallel sentences, creating a bilingual “database” of translations
Decoding: new sentences are translated by a program (the decoder), which matches the source words and phrases with the database of translations, and searches the “space” of all possible translation combinations.
February 26, 2009
LTI OH 2009

37. Statistical MT (SMT)
Main steps in training phrase-based statistical MT:
Create a sentence-aligned parallel corpus
Word Alignment: train word-level alignment models (GIZA++)
Phrase Extraction: extract phrase-to-phrase translation correspondences using heuristics (Pharoah)
Minimum Error Rate Training (MERT): optimize translation system parameters on development data to achieve best translation performance
Attractive: completely automatic, no manual rules, much reduced manual labor
Main drawbacks:
Translation accuracy levels vary
Effective only with large volumes (several mega-words) of parallel text
Broad domain, but domain-sensitive
Still viable only for small number of language pairs!
Impressive progress in last 5 years
February 26, 2009
LTI OH 2009

38. Matches to Source Found
EBMT Paradigm
New Sentence (Source)
Yesterday, 200 delegates met with President Clinton.
Matches to Source Found
Yesterday, 200 delegates met behind closed doors…
Difficulties with President Clinton…
Gestern trafen sich 200 Abgeordnete hinter verschlossenen…
Schwierigkeiten mit Praesident Clinton…
Alignment (Sub-sentential)
Yesterday, 200 delegates met behind closed doors…
Difficulties with President Clinton over…
Gestern trafen sich 200 Abgeordnete hinter verschlossenen…
Schwierigkeiten mit Praesident Clinton…
Translated Sentence (Target)
February 26, 2009
LTI OH 2009
Gestern trafen sich 200 Abgeordnete mit Praesident Clinton.

39. Transfer Approaches Syntactic Transfer: Semantic Transfer:
Analyze SL input sentence to its syntactic structure (parse tree)
Transfer SL parse-tree to TL parse-tree (various formalisms for specifying mappings)
Generate TL sentence from the TL parse-tree
Semantic Transfer:
Analyze SL input to a language-specific semantic representation (i.e., Case Frames, Logical Form)
Transfer SL semantic representation to TL semantic representation
Generate syntactic structure and then surface sentence in the TL
February 26, 2009
LTI OH 2009

40. Transfer Approaches Main Advantages and Disadvantages:
Syntactic Transfer:
No need for semantic analysis and generation
Syntactic structures are general, not domain specific  Less domain dependent, can handle open domains
Requires word translation lexicon
Semantic Transfer:
Requires deeper analysis and generation, symbolic representation of concepts and predicates  difficult to construct for open or unlimited domains
Can better handle non-compositional meaning structures  can be more accurate
No word translation lexicon – generate in TL from symbolic concepts
February 26, 2009
LTI OH 2009

41. The METEOR Metric Example: P = 5/8 =0.625 R = 5/14 = 0.357
Reference: “the Iraqi weapons are to be handed over to the army within two weeks”
MT output: “in two weeks Iraq’s weapons will give army”
Matching: Ref: Iraqi weapons army two weeks
MT: two weeks Iraq’s weapons army
P = 5/8 = R = 5/14 = 0.357
Fmean = 10*P*R/(9P+R) =
Fragmentation: 3 frags of 5 words = (3-1)/(5-1) = 0.50
Discounting factor: DF = 0.5 * (frag**3) =
Final score: Fmean * (1- DF) = * =
February 26, 2009
LTI OH 2009

42. Synthetic Combination MEMT
Two Stage Approach:
Align: Identify common words and phrases across the translations provided by the engines
Decode: search the space of synthetic combinations of words/phrases and select the highest scoring combined translation
Example:
announced afghan authorities on saturday reconstituted four intergovernmental committees
The Afghan authorities on Saturday the formation of the four committees of government
February 26, 2009
LTI OH 2009

43. Synthetic Combination MEMT
Two Stage Approach:
Align: Identify common words and phrases across the translations provided by the engines
Decode: search the space of synthetic combinations of words/phrases and select the highest scoring combined translation
Example:
announced afghan authorities on saturday reconstituted four intergovernmental committees
The Afghan authorities on Saturday the formation of the four committees of government
MEMT: the afghan authorities announced on Saturday the formation of four intergovernmental committees
February 26, 2009
LTI OH 2009