Presentation is loading. Please wait.

Presentation is loading. Please wait.

Machine Translation Overview

Similar presentations


Presentation on theme: "Machine Translation Overview"— Presentation transcript:

1 Machine Translation Overview
Alon Lavie Language Technologies Institute Carnegie Mellon University LTI Open House February 23, 2012

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 February 23, 2012 LTI Open House 2012

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. Software Localization and documentation dissemination for large manufacturers (Microsoft, Intel, Apple, EBay, ALCOA, etc.) Language and translation services business sector estimated at $26 Billion worldwide in 2010 and growing at a healthy pace Volume of online content growing exponentially Economic incentive is still primarily within a small number of language pairs Some fairly decent commercial products in the market for these language pairs Product of rule-based systems after many years of development: SYSTRAN, PROMT, others… New generation of data-driven “statistical” MT systems: SDL/Language Weaver, Asia Online, Safaba, others… Web-based (mostly free) MT services: Google, MS-Bing, Babelfish, others… Pervasive MT between many language pairs still non-existent, but some significant progress in recent years February 23, 2012 LTI Open House 2012

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? February 23, 2012 LTI Open House 2012

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? February 23, 2012 LTI Open House 2012

6 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: PROMT’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: Google’s Statistical MT systems. Learning Approaches: learn translation rules automatically from linguistically annotated human translated and word-aligned data. Example: Syntax-based SMT approaches. Simplify the Problem: build systems that are limited-domain or constrained in other ways. Example: CMU’s limited-domain speech translation. February 23, 2012 LTI Open House 2012

7 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 February 23, 2012 LTI Open House 2012

8 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 February 23, 2012 LTI Open House 2012

9 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 language and data scenarios, it actually works better! February 23, 2012 LTI Open House 2012

10 Statistical MT (SMT) Data-driven, most dominant approach in current MT research Originally 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 sub-sentential translation candidates Decoding: new sentences are translated by a computer 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 23, 2012 LTI Open House 2012

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! Optimization is brittle, problematic and metric-dependent! Solutions: Google solution: more and more data! Research solution: “smarter” algorithms and learning methods February 23, 2012 LTI Open House 2012

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 February 23, 2012 LTI Open House 2012

13 Representative Example: Google Translate
February 23, 2012 LTI Open House 2012

14 Google Translate February 23, 2012 LTI Open House 2012

15 Google Translate February 23, 2012 LTI Open House 2012

16 Types of MT Applications:
Assimilation: multiple source languages  one target language, uncontrolled style/topic. Dissemination: one source language  multiple target languages, often controlled style, single topic/domain. Communication: Speech, chat, text messages. Real-time is critical. Lower quality may be okay due to collaborative setting. February 23, 2012 LTI Open House 2012

17 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 23, 2012 LTI Open House 2012

18 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 23, 2012 LTI Open House 2012

19 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 23, 2012 LTI Open House 2012

20 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 Active research on all main approaches to MT Leader in the area of speech-to-speech MT Multi-Engine MT (MEMT) MT Evaluation (METEOR) Spin-off Companies: Jibbigo (speech translation on mobile devices) Safaba (MT solutions for enterprises and LSPs) February 23, 2012 LTI Open House 2012

21 MT Faculty at LTI Alon Lavie Ralf Brown Jaime Carbonell Lori Levin
Noah Smith Alan Black Bob Frederking Florian Metze Alex Waibel Teruko Mitamura Eric Nyberg February 23, 2012 LTI Open House 2012

22 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 Effective Target Language Modeling Context-dependent modeling and adaptation Novel algorithms for model acquisition and decoding February 23, 2012 LTI Open House 2012

23 Questions… February 23, 2012 LTI Open House 2012

24 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 23, 2012 LTI Open House 2012

25 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) February 23, 2012 LTI Open House 2012

26 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 23, 2012 LTI Open House 2012

27 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 23, 2012 LTI Open House 2012

28 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 23, 2012 LTI Open House 2012

29 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 February 23, 2012 LTI Open House 2012

30 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 23, 2012 LTI Open House 2012

31 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 23, 2012 LTI Open House 2012

32 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 February 23, 2012 LTI Open House 2012

33 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 February 23, 2012 LTI Open House 2012

34 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 February 23, 2012 LTI Open House 2012

35 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 February 23, 2012 LTI Open House 2012

36 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 23, 2012 LTI Open House 2012

37 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 23, 2012 LTI Open House 2012

38 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 23, 2012 LTI Open House 2012

39 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 23, 2012 LTI Open House 2012

40 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 23, 2012 LTI Open House 2012

41 Formulaic Utterances Good night. tisbaH cala xEr waking up on good
Romanization of Arabic from CallHome Egypt February 23, 2012 LTI Open House 2012

42 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 23, 2012 LTI Open House 2012

43 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 23, 2012 LTI Open House 2012

44 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 23, 2012 LTI Open House 2012

45 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 23, 2012 LTI Open House 2012

46 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 23, 2012 LTI Open House 2012 Gestern trafen sich 200 Abgeordnete mit Praesident Clinton.

47 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 23, 2012 LTI Open House 2012

48 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 23, 2012 LTI Open House 2012

49 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 23, 2012 LTI Open House 2012

50 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 23, 2012 LTI Open House 2012

51 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 23, 2012 LTI Open House 2012

52 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! February 23, 2012 LTI Open House 2012


Download ppt "Machine Translation Overview"

Similar presentations


Ads by Google