1 / 52

Machine Translation Overview

Machine Translation Overview. Alon Lavie Language Technologies Institute Carnegie Mellon University LTI Immigration Course August 16, 2010. Machine Translation: History. 1946: MT is one of the first conceived applications of modern computers (A.D. Booth, Alan Turing)

jarvis
Download Presentation

Machine Translation Overview

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Machine Translation Overview Alon Lavie Language Technologies Institute Carnegie Mellon University LTI Immigration Course August 16, 2010

  2. Machine Translation: History • 1946: MT is one of the first conceived applications of modern computers (A.D. Booth, Alan Turing) • 1954: The “Georgetown Experiment” Promising “toy” demonstrations of Russian-English MT • Late 1950s and early 1960s: MT fails to scale up to “real” systems • 1966: ALPAC Report: MT recognized as an extremely difficult, “AI-complete” problem. Funding disappears • 1968: SYSTRAN founded • 1985: CMU “Center for Machine Translation” (CMT) founded • Late 1980s and early 1990s: Field dominated by rule-based approaches – KBMT, KANT, Eurotra, etc. • 1992: “Noisy Channel” Statistical MT models invented by IBM researchers (Brown, Della Pietra, et al.). CANDIDE • Mid 1990s: First major DARPA MT Program. PANGLOSS • Late 1990s: Major Speech-to-Speech MT demonstrations: C-STAR • 1999: JHU Summer Workshop results in GIZA • 2000s: Large DARPA Funding Programs – TIDES and GALE • 2003: Och et al introduce Phrase-based SMT. PHARAOH • 2006: Google Translate is launched • 2007: Koehn et al release MOSES LTI IC 2010

  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, Intel, Apple, Caterpillar, US Steel, ALCOA, etc.) • 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! LTI IC 2010

  4. How Does MT Work? • All modern MT approaches are based on building translations for complete sentences 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? LTI IC 2010

  5. 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? LTI IC 2010

  6. 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 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 LTI IC 2010

  7. 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 LTI IC 2010

  8. 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! LTI IC 2010

  9. Statistical MT (SMT) Data-driven, most dominant approach in current MT research Proposed by IBM in early 1990s: a direct, purely statistical, model for MT 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. LTI IC 2010

  10. 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 (Moses) 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 widely Effective only with large volumes (several mega-words) of parallel text Broad domain, but domain-sensitive Viable only for limited number of language pairs! Impressive progress in last 5-10 years! LTI IC 2010

  11. Statistical MT: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 properly 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! • MERT is brittle, problematic and metric-dependent! • Solutions: • Google solution: more and more data! • Research solution: “smarter” algorithms and learning methods LTI IC 2010

  12. 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-based Data-driven LTI IC 2010

  13. Representative Example: Google Translate • http://translate.google.com LTI IC 2010

  14. Google Translate LTI IC 2010

  15. Google Translate LTI IC 2010

  16. 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 LTI IC 2010

  17. 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!. LTI IC 2010

  18. 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 (Post-editing) LTI IC 2010

  19. 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. LTI IC 2010

  20. 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 LTI IC 2010

  21. 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? LTI IC 2010

  22. Interlingua versus Transfer • With interlingua, need only N parsers/ generators instead of N2 transfer systems: L2 L2 L3 L1 L1 L3 interlingua L6 L4 L6 L4 L5 L5 LTI IC 2010

  23. 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 LTI IC 2010

  24. 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? LTI IC 2010

  25. 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) LTI IC 2010

  26. MT Faculty at LTI • Alon Lavie • Stephan Vogel • Ralf Brown • Jaime Carbonell • Lori Levin • Noah Smith • Alan Black • Florian Metze • Alex Waibel • Teruko Mitamura • Eric Nyberg LTI IC 2010

  27. 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 LTI IC 2010

  28. CMU Statistical Transfer (Stat-XFER) MT Approach Integrate the major strengths of rule-based and statistical MT within a common syntax-based 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 syntax-driven 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, effective syntactic modeling, MT for low-resource languages Contact Faculty: Alon Lavie, Lori Levin, Bob Frederking and Jaime Carbonell LTI IC 2010

  29. 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 LTI IC 2010

  30. 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 LTI IC 2010

  31. 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 • Some active follow-on projects • Contact Faculty: Eric Nyberg and Teruko Mitamura LTI IC 2010

  32. Multi-Engine MT • 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 a variety of features, including n-gram support and Language Model • Parameter Tuning: Learn optimal weights using MERT • 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 LTI IC 2010

  33. Automated MT Evaluation • METEOR: Automated 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 and paraphrases • Address fluency/grammaticality via a direct penalty: how well-ordered is the matching of the MT output with the reference? • Tunable Weights: Weights for Precision, Recall, Fragmentation are tuned for optimal correlation with human judgments • Outcome: Much improved levels of correlation! • Contact Faculty: Alon Lavie LTI IC 2010

  34. Safaba Translation Solutions • Recent CMU commercial spin-off company in the MT area • Mission: Develop and deliver advanced translation automation software solutions for the commercial translation business sector • Target Clients: Language Services Providers (LSPs) and their enterprise clients • Primary Service: • Software-as-a-Service customized MT Technology: Develop specialized highly-scalable software for delivering high-quality client-customized Machine Translation (MT) based on a low-cost SaaS model • Other Related Services: • Consulting Services: Analyze LSP/client translation processes and technologies and advise clients on effective solutions for increasing their translation automation • Software Implementation Services: Design and implement custom translation automation solutions for LSPs and/or enterprise clients • Contact Faculty: Alon Lavie LTI IC 2010

  35. 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 structural mappings between languages from parallel word-aligned data • overcoming syntax-to-semantics differences and dealing with constructions • Stronger Target Language Modeling • Novel algorithms for model acquisition and decoding LTI IC 2010

  36. Questions… LTI IC 2010

  37. 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 snubdoesn’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) LTI IC 2010

  38. 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) LTI IC 2010

  39. 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 LTI IC 2010

  40. 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 LTI IC 2010

  41. 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? LTI IC 2010

  42. Formulaic Utterances • Good night. • tisbaH cala xEr waking up on good • Romanization of Arabic from CallHome Egypt LTI IC 2010

  43. Analysis and GenerationMain 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 LTI IC 2010

  44. 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) LTI IC 2010

  45. 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. LTI IC 2010

  46. 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 LTI IC 2010

  47. 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) LTI IC 2010 Gestern trafen sich 200 Abgeordnete mit Praesident Clinton.

  48. 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 semanticrepresentation (i.e., Case Frames, Logical Form) • Transfer SL semantic representation to TL semantic representation • Generate syntactic structure and then surface sentence in the TL LTI IC 2010

  49. 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 LTI IC 2010

  50. The METEOR Metric • Example: • Reference: “the Iraqi weaponsare 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 LTI IC 2010

More Related