1. Machine Translation: Approaches, Challenges and Future Alon Lavie Language Technologies Institute School of Computer Science Carnegie Mellon University ITEC Dinner May 21, 2009

2. ITEC Dinner2 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 ALPAC 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) Major paradigm shift in MT over the past decade: –From manually developed rule-based systems –To Data-driven statistical search-based approaches

3. May 21, 2009ITEC Dinner3 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, US Steel, ALCOA) –Language and translation services business sector estimated at $15 Billion worldwide in 2008 and growing at a healthy pace Economic incentive is still primarily within a small number of language pairs Some fairly decent commercial products in the market for these language pairs –Primarily a product of rule-based systems after many years of development –New generation of data-driven “statistical” MT: Google, Language Weaver Web-based (mostly free) MT services: Google, Babelfish, others… Pervasive MT between many language pairs still non-existent, but Google is trying to change that!

4. May 21, 2009ITEC Dinner4 Representative Example: Google Translate http://translate.google.com

5. May 21, 2009ITEC Dinner5 Google Translate

6. 6

7. May 21, 2009ITEC Dinner7 Example of High-Quality Rule-based 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.

8. May 21, 2009ITEC Dinner8 Machine Translation: Some Basic Terminology Source Language (SL): the language of the original text that we wish to translate Target Language (TL): the language into which we wish to translate Translation Segment: language “unit” which is translated independently; usually sentences, sometimes smaller phrases or terms

9. May 21, 2009ITEC Dinner9 How Does MT Work? Naïve MT: Translation Memory –Store in a database human translations of sentences (or shorter phrases) that have been already translated before –When translating a new document: For each source sentence, search the DB to see if it has been translated before If found, retrieve it’s translation! “Fuzzy matches”, multiple translations –Main Advantage: translation output is always human- quality! –Main Disadvantage: many/most sentences haven’t been translated before, cannot be retrieved… Translation Memories are heavily used by the Commercial Language Service Provider Industry – companies such as Echo International

10. May 21, 2009ITEC Dinner10 How Does MT Work? All modern MT approaches are based on building translations for complete segments by putting together smaller pieces of translation Core Questions: –What are these smaller pieces of translation? Where do they come from? –How does MT put these pieces together? –How does the MT system pick the correct (or best) translation among many options?

11. May 21, 2009ITEC Dinner11 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?

12. May 21, 2009ITEC Dinner12 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: CMU’s Statistical XFER approach. Simplify the Problem: build systems that are limited- domain or constrained in other ways. Example: CATLYST system built for Caterpillar

13. May 21, 2009ITEC Dinner13 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

14. May 21, 2009ITEC Dinner14 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)

15. May 21, 2009ITEC Dinner15 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)

16. May 21, 2009ITEC Dinner16 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

17. May 21, 2009ITEC Dinner17 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?

18. May 21, 2009ITEC Dinner18 Formulaic Utterances Good night. tisbaH cala xEr waking up on good Romanization of Arabic from CallHome Egypt

19. May 21, 2009ITEC Dinner19 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: Data-driven (Statistical) MT –GP HQ: Include humans in the MT-loop – post-editing!

20. May 21, 2009ITEC Dinner20 Types of MT Applications: Assimilation: multiple source languages, uncontrolled style/topic. Requires general purpose MT: good fit for “Google Translate” Dissemination: one source language, into multiple target languages; often controlled style, single topic/domain (at least per user): this is the common commercial translation scenario: good fit for KBMT and customized Statistical MT Communication: Lower quality may be okay, but system robustness, real-time required.

21. May 21, 2009ITEC Dinner21 Mi chiamo Alon LavieMy name is Alon Lavie Give-information+personal-data (name=alon_lavie) [ s [ vp accusative_pronoun “chiamare” proper_name]] [ s [ np [possessive_pronoun “name”]] [ vp “be” proper_name]] Direct Transfer Interlingua Analysis Generation Approaches to MT: Vaquois MT Triangle

22. May 21, 2009ITEC Dinner22 Interlingua versus Transfer With interlingua, need only N parsers/ generators instead of N 2 transfer systems: L1 L2 L3 L4 L5 L6 L1 L2 L3 L6 L5 L4 interlingua

23. May 21, 2009ITEC Dinner23 Rule-based vs. Data-driven Approaches to MT What are the pieces of translation? Where do they come from? –Rule-based: large-scale “clean” word translation lexicons, manually constructed over time by human experts –Data-driven: broad-coverage word and multi-word translation lexicons, learned automatically from available sentence-parallel corpora How does MT put these pieces together? –Rule-based: large collections of rules, manually developed over time by human experts, that map structures from the source to the target language –Data-driven: a computer algorithm that explores millions of possible ways of putting the small pieces together, looking for the translation that statistically looks best

24. May 21, 2009ITEC Dinner24 Rule-based vs. Data-driven Approaches to MT How does the MT system pick the correct (or best) translation among many options? –Rule-based: Human experts encode preferences among the rules designed to prefer creation of better translations –Data-driven: a variety of fitness and preference scores, many of which can be learned from available training data, are used to model a total score for each of the millions of possible translation candidates; algorithm then selects and outputs the best scoring translation

25. May 21, 2009ITEC Dinner25 Rule-based vs. Data-driven Approaches to MT Why have the data-driven approaches become so popular? –We can now do this! Increasing amounts of sentence-parallel data are constantly being created on the web Advances in machine learning algorithms Computational power of today’s computers can train systems on these massive amounts of data and can perform these massive search-based translation computations when translating new texts –Building and maintaining rule-based systems is too difficult, expensive and time-consuming –In many scenarios, it actually works better!

26. May 21, 2009ITEC Dinner26 Rule-based vs. Data-driven MT We thank all participants of the whole world for their comical and creative drawings; to choose the victors was not easy task! Click here to see work of winning European of these two months, and use it to look at what the winning of USA sent us. We thank all the participants from around the world for their designs cocasses and creative; selecting winners was not easy! Click here to see the artwork of winners European of these two months, and disclosure to look at what the winners of the US have been sending. Rule-basedData-driven

27. May 21, 2009ITEC Dinner27 Data-driven MT: Some Major Challenges Current approaches are too naïve and “direct”: –Good at learning word-to-word and phrase-to-phrase correspondences from data –Not good enough at learning how to combine these pieces and reorder them during translation –Learning general rules requires much more complicated algorithms and computer processing of the data –The space of translations that is “searched” often doesn’t contain a perfect translation –The fitness scores that are used aren’t good enough to always assign better scores to the better translations  we don’t always find the best translation even when it’s there! Solutions: –Google solution: more and more data! –Research solution: “smarter” algorithms and learning methods

28. May 21, 2009ITEC Dinner28 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

29. May 21, 2009ITEC Dinner29 Synthetic Combination MEMT Two Stage Approach: 1.Align: Identify common words and phrases across the translations provided by the engines 2.Decode: search the space of synthetic combinations of words/phrases and select the highest scoring combined translation Example: 1.announced afghan authorities on saturday reconstituted four intergovernmental committees 2.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

30. May 21, 2009ITEC Dinner30 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 (SR) 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?

31. May 21, 2009ITEC Dinner31 MT Evaluation How do you evaluate the quality of the output of MT systems? Human notions of translation quality: –Adequacy: to what extent does the translation have the same meaning as the original sentence? –Fluency: to what extent is the translation fluent and grammatical in the target language –Rankings: given two (or more) translations of the same input sentence, which one is better? (Or rank them by quality) –Task-based measures: is the translation sufficient for accomplishing a specific task or goal (i.e. understanding the gist of the document, flagging important documents that should be translated by a human)

32. May 21, 2009ITEC Dinner32 Automated MT Evaluation Automatic Evaluation Metrics are extremely important: –Human evaluations are too expensive and time consuming to be done very frequently –Need to test changes and assess whether system is getting better quickly and on an on-going basis –Data-driven MT systems have lots of tunable parameters – need to optimize them for best performance Goal: Fully automatic fast metric that can assess quality and that correlates well with human notions of quality Major Approach: –Obtain human “reference” translations for test data sets –Estimate how “close” the MT translations are to the human translations (on a scale of [0,1]) Major Challenge: translation variability – there are many correct translations. How to measure similarity?

33. May 21, 2009ITEC Dinner33 MT for Commercial Language Service Providers Most dissemination-type high-quality translation is performed by commercial Language service provider (LSP) companies, such as Echo International Translation process used by most LSPs: –Heavily dependent on expensive human translators, to ensure high-quality –Current automation mostly in the form of Translation Memories: Previously translated segments don’t have to be translated again by human translators The retrieved translations are of guaranteed high- quality – limited post-editing is required –No extensive use of modern state-of-the-art MT!

34. May 21, 2009ITEC Dinner34 MT for Commercial Language Service Providers Why is MT currently not used by LSPs? –The quality of translations produced by MT varies widely: some sentences can be perfect translations, others can be very bad –Post-editing bad MT output using human translators is frustrating and unappealing, and is often not cost- effective –No existing good technical solutions that integrate MT seamlessly within the existing translation workflow processes used by LSPs –LSPs are wary of taking a “leap of faith” on unproven technology that may not save money

35. May 21, 2009ITEC Dinner35 Safaba Translation Solutions LLC New CMU spin-off technology start-up company Mission: Develop innovative solutions using automated Machine Translation for commercial Language Service Providers (LSPs) Concept: –Identify and enhance high-quality automatically-produced translations and efficiently integrate them into the human translation loop, dramatically reducing cost and turn-around times of translation projects for commercial LSPs Founders: –Alon Lavie – Associate Research Professor, LTI, CMU –Robert Olszewski – CMU CS Ph.D. (2001) Partnering with Echo International for feasibility analysis and as a potential primary beta-testing client

36. May 21, 2009ITEC Dinner36 Some Take-home Messages Machine Translation is already quite good for many purposes and needs, and is getting better all the time Modern state-of-the-art MT is data-driven – computers learning from data. This paradigm shift is not reversible For casual (assimilation-type) needs, free web-based translation services such as Google are already very useful For business (dissemination-type) needs, LSPs are usually required, but MT will increasingly integrate into the way LSPs do translation

37. May 21, 2009ITEC Dinner37 Questions…

38. May 21, 2009ITEC Dinner38 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)

39. May 21, 2009ITEC Dinner39 Google at Work…

40. May 21, 2009ITEC Dinner40

41. May 21, 2009ITEC Dinner41

42. May 21, 2009ITEC Dinner42 Lexical Differences Lexical gaps: –Examples: these have no direct equivalent in English: gratiner (v., French, “to cook with a cheese coating”) ōtosanrin (n., Japanese, “three-wheeled truck or van”)

43. May 21, 2009ITEC Dinner43 [From Hutchins & Somers] Lexical Differences

44. May 21, 2009ITEC Dinner44 MT Handling of Lexical Differences Direct MT and Syntactic Transfer: –Lexical Transfer stage uses bilingual lexicon –SL word can have multiple translation entries, possibly augmented with disambiguation features or probabilities –Lexical Transfer can involve use of limited context (on SL side, TL side, or both) –Lexical Gaps can partly be addressed via phrasal lexicons Semantic Transfer: –Ambiguity of SL word must be resolved during analysis  correct symbolic representation at semantic level –TL Generation must select appropriate word or structure for correctly conveying the concept in TL

45. May 21, 2009ITEC Dinner45 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)

46. May 21, 2009ITEC Dinner46

47. May 21, 2009ITEC Dinner47

48. May 21, 2009ITEC Dinner48

49. May 21, 2009ITEC Dinner49 MT Handling of Structural Differences Direct MT Approaches: –No explicit treatment: Phrasal Lexicons and sentence level matches or templates Syntactic Transfer: –Structural Transfer Grammars Trigger rule by matching against syntactic structure on SL side Rule specifies how to reorder and re-structure the syntactic constituents to reflect syntax of TL side Semantic Transfer: –SL Semantic Representation abstracts away from SL syntax to functional roles  done during analysis –TL Generation maps semantic structures to correct TL syntax

50. May 21, 2009ITEC Dinner50 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  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

51. May 21, 2009ITEC Dinner51 Syntax-to-Semantics Differences Structure-change example: I like swimming “Ich scwhimme gern” I swim gladly

52. May 21, 2009ITEC Dinner52

53. May 21, 2009ITEC Dinner53 Syntax-to-Semantics Differences Verb-argument example: Jones likes the film. “Le film plait à Jones.” (lit: “the film pleases to Jones”) Use of case roles can eliminate the need for this type of transfer – Jones = Experiencer – film = Theme

54. May 21, 2009ITEC Dinner54

55. May 21, 2009ITEC Dinner55

56. May 21, 2009ITEC Dinner56 Syntax-to-Semantics Differences Passive Constructions Example: French reflexive passives: Ces livres se lisent facilement *”These books read themselves easily” These books are easily read

57. May 21, 2009ITEC Dinner57

58. May 21, 2009ITEC Dinner58

59. May 21, 2009ITEC Dinner59 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)

60. May 21, 2009ITEC Dinner60 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.

61. May 21, 2009ITEC Dinner61 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

62. May 21, 2009ITEC Dinner62 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) Translated Sentence (Target) Gestern trafen sich 200 Abgeordnete mit Praesident Clinton. Yesterday, 200 delegates met behind closed doors… Difficulties with President Clinton over… Gestern trafen sich 200 Abgeordnete hinter verschlossenen… Schwierigkeiten mit Praesident Clinton…

63. May 21, 2009ITEC Dinner63 Transfer Approaches Syntactic 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

64. May 21, 2009ITEC Dinner64 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

65. May 21, 2009ITEC Dinner65 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)

66. May 21, 2009ITEC Dinner66 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

67. May 21, 2009ITEC Dinner67 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

68. May 21, 2009ITEC Dinner68 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

69. May 21, 2009ITEC Dinner69 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

70. May 21, 2009ITEC Dinner70 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

71. May 21, 2009ITEC Dinner71 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

72. May 21, 2009ITEC Dinner72 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

73. May 21, 2009ITEC Dinner73 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

74. May 21, 2009ITEC Dinner74 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?

75. May 21, 2009ITEC Dinner75 Analysis and Generation Main Steps Analysis: –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

76. May 21, 2009ITEC Dinner76 The METEOR Metric Example: –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 =0.625 R = 5/14 = 0.357 Fmean = 10*P*R/(9P+R) = 0.3731 Fragmentation: 3 frags of 5 words = (3-1)/(5-1) = 0.50 Discounting factor: DF = 0.5 * (frag**3) = 0.0625 Final score: Fmean * (1- DF) = 0.3731*0.9375 = 0.3498

77. May 21, 2009ITEC Dinner77 Synthetic Combination MEMT Two Stage Approach: 1.Align: Identify common words and phrases across the translations provided by the engines 2.Decode: search the space of synthetic combinations of words/phrases and select the highest scoring combined translation Example: 1.announced afghan authorities on saturday reconstituted four intergovernmental committees 2.The Afghan authorities on Saturday the formation of the four committees of government

78. May 21, 2009ITEC Dinner7810/10/2015Alon Lavie: Stat-XFER78 Translation Lexicon: Hebrew-to-English Examples (Semi-manually-developed) 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") )

79. May 21, 2009ITEC Dinner7910/10/2015Alon Lavie: Stat-XFER79 Translation Lexicon: French-to-English Examples (Automatically-acquired) DET::DET |: [“le"] -> [“the"] ( (X1::Y1) ) Prep::Prep |:[“dans”] -> [“in”] ( (X1::Y1) ) N::N |: [“principes"] -> [“principles"] ( (X1::Y1) ) N::N |: [“respect"] -> [“accordance"] ( (X1::Y1) ) NP::NP |: [“le respect"] -> [“accordance"] ( ) PP::PP |: [“dans le respect"] -> [“in accordance"] ( ) PP::PP |: [“des principes"] -> [“with the principles"] ( )

80. May 21, 2009ITEC Dinner8010/10/2015Alon Lavie: Stat-XFER80 Hebrew-English Transfer Grammar Example Rules (Manually-developed) {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) )

81. May 21, 2009ITEC Dinner8110/10/2015Alon Lavie: Stat-XFER81 French-English Transfer Grammar Example Rules (Automatically-acquired) {PP,24691} ;;SL: des principes ;;TL: with the principles PP::PP [“des” N] -> [“with the” N] ( (X1::Y1) ) {PP,312} ;;SL: dans le respect des principes ;;TL: in accordance with the principles PP::PP [Prep NP] -> [Prep NP] ( (X1::Y1) (X2::Y2) )

82. May 21, 2009ITEC Dinner82 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