Machine Translation: Approaches, Challenges and Future Alon Lavie Language Technologies Institute Carnegie Mellon University ITEC Dinner May 21, 2009

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

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) –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 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!

May 21, 2009ITEC Dinner4 Representative Example: Google Translate

May 21, 2009ITEC Dinner5 Google Translate

6

May 21, 2009ITEC Dinner7 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.

May 21, 2009ITEC Dinner8 Machine Translation: 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 “units” which are translated independently, usually sentences, sometimes smaller phrases or terms

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 Translation Service Provider Industry – companies such as Echo International

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 Issues: –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?

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?

May 21, 2009ITEC Dinner12 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

May 21, 2009ITEC Dinner13 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!.

May 21, 2009ITEC Dinner14 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)

May 21, 2009ITEC Dinner15 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.

May 21, 2009ITEC Dinner16 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

May 21, 2009ITEC Dinner17 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?

May 21, 2009ITEC Dinner18 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

May 21, 2009ITEC Dinner19 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

May 21, 2009ITEC Dinner20 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?

May 21, 2009ITEC Dinner21 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

May 21, 2009ITEC Dinner22 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

May 21, 2009ITEC Dinner23 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

May 21, 2009ITEC Dinner24 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

May 21, 2009ITEC Dinner25 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

May 21, 2009ITEC Dinner26 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

May 21, 2009ITEC Dinner27 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

May 21, 2009ITEC Dinner28 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)

May 21, 2009ITEC Dinner29 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

May 21, 2009ITEC Dinner30 Questions…

May 21, 2009ITEC Dinner31 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)

May 21, 2009ITEC Dinner32 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)

May 21, 2009ITEC Dinner33 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

May 21, 2009ITEC Dinner34 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

May 21, 2009ITEC Dinner35 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?

May 21, 2009ITEC Dinner36 Formulaic Utterances Good night. tisbaH cala xEr waking up on good Romanization of Arabic from CallHome Egypt

May 21, 2009ITEC Dinner37 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

May 21, 2009ITEC Dinner38 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)

May 21, 2009ITEC Dinner39 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.

May 21, 2009ITEC Dinner40 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

May 21, 2009ITEC Dinner41 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…

May 21, 2009ITEC Dinner42 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

May 21, 2009ITEC Dinner43 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

May 21, 2009ITEC Dinner44 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 = 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) = * =

May 21, 2009ITEC Dinner45 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

May 21, 2009ITEC Dinner46 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