Architectures for MT - direct, transfer and "Interlingua"

Architectures for MT - direct, transfer and "Interlingua"

Architectures for MT direct, transfer and Interlingua Lecture 28/01/2008 MODL5003 Principles and applications of machine translation Bogdan Babych, [email protected] Tony Hartley, [email protected] 1 1. Overview Classification of approaches to MT Architectures of rule-based MT systems

the MT triangle Reviewing each architecture and its problems Architectures compared Limits of MT 2 2. Architectural challenges for MT : 1/2 Rule-based approaches (lecture today) Direct MT Transfer MT Interlingua MT Use formal models of our knowledge of language to explicate human knowledge used for translation,

put it into an Expert System Problems expensive to build require precise knowledge, which might be not available 3 2. Architectural challenges for MT : 2/2 Corpus-based approaches (lecture 21/04/2008) Example-based MT Statistical MT Use machine learning techniques on large collections of available parallel texts

"to let the data speak for themselves Problems: language data are sparse (difficult to achieve saturation) high-quality linguistic resources are also expensive Corpus-based support for rule-based approaches 4 3. Possible Architecture of MT systems (the MT triangle) **Interlingua = language independent representation of a text 5

Direct n (n 1) modules 5 languages = 20 modules Transfer n (n 1) transfer n (n + 1) in total = 30 modules in total Interlingua n 2 modules 5 languages = 10 modules 6

4. Direct systems Essentially: word for word translation with some attention to local linguistic context No linguistic representation is built (historically come first: the Georgetown experiment 1954-1963: 250 words, 6 grammar rules, 49 sentences) Sentence: The questions are difficult (P.Bennett, 2001) (algorithm: a "window" of a limited size moves through the text and checks if any rules match) 1. the <[N.plur]> les /*before plural noun*/ 2. <[article]> questions [N.plur]/*'questions' is plur. noun after the questions

article */ 3. <[not: "we" or "you"]> are /* unless it follows the words "we" or sont "you"*/ 4. difficult difficilles /*when it follows 'are'*/ 7 direct systems: advantages Technical: Machine-learning can be easily applied It is straightforward to learn direct rules Intermediate representations are more difficult Linguistic: Exploiting structural similarity between languages

similarity is not accidental historic, typological, based on language and cognitive universals High-quality MT for direct systems between closely-related languages 8 A. direct systems: technical problems 1/2 rules are "tactical", not "strategic" (do not generalise) have little linguistic significance no obvious link between our ideas about translation and the formalism large systems are difficult to maintain and to

develop: systems become non-manageable interaction of a large number of rules: rules are not completely independent 9 A. direct systems: technical problems 2/2 no reusability a new set of rules is required for each language pair no knowledge can be reused for new language pairs

Rules are complex and specific to translation direction 10 B. direct systems: linguistic problems: Information for disambiguation appears not locally context length cannot be predicted in advanced Hard to handle for direct systems: Lexical Mismatch (no 1 to 1 correspondence between words)

Structural Mismatch (no 1 to 1 correspondence between constructions) 11 B1. Lexical Mismatch: 1/2 Das ist ein starker Mann This is a strong man Es war sein strkstes Theaterstck It has been his best play Wir hoffen auf eine starke Beteiligung We hope a large number of people will take part Eine 100 Mann starke Truppe A 100 strong unit Der starke Regen berraschte uns

We were surprised by the heavy rain Maria hat starkes Interesse gezeigt Mary has shown strong interest Paul hat starkes Fieber Paul has high temperature Das Auto war stark beschdigt The car was badly damaged Das Stck fand einen starken The piece had a considerable response Widerhall Das Essen was stark gewrzt The meal was strongly seasoned Hans ist ein starker Raucher John is a heavy smoker Er hatte daran starken Zweifel He had grave doubts about it

(example by John Hutchins, 2002) 12 B1. Lexical Mismatch: 2/2 The questions are hard hard difficile dur + Non-local context for disambiguation The questions she tackled yesterday seemed very hard To bake tasty bread is very hard 13 B2. Structural Mismatch

(1/2) EN: I will go to see my GP tomorrow JP: Watashi wa asu isha ni mite morau Lit: 'I will ask my GP to check me tomorrow' EN: The bottle floated out of the cave ES: La botella sali de la cueva (flotando) Lit.: the bottle moved-out from the cave (floating) Same meaning is typically expressed by different structures 14 B2. Structural Mismatch (2/2)

1. The question N changes every day V Ukr.: N.nom . V Pytann'a .N.nom min'ajet's'a. V shchodn'a 2. The question .N changes have been agreed N Ukr.: 3. The question .N changes have been difficult

N Ukr.: . N.acc. N.gen Zminu N.acc pytan' N.gen bulo pohodzheno . N.nom. N.gen Zmin a N.nom pytan' N.gen bul a skladnoju translation of the word question is also different, because its function in a phrase has changed translation might depend on the overall structure even if the function does not change in the English sentence

15 5. Indirect systems 16 5. Indirect systems linguistic analysis of the ST some kind of linguistic representation (Interface or Intermediate Representation -- IR) ST Interface Representation(s) TT Transfer systems: -- IRs are language-specific -- Language-pair specific mappings are used Interlingual systems:

-- IRs are language-independent -- No language-pair specific mappings 17 6. Transfer systems 3 stages: Analysis - Transfer Synthesis Analysis and synthesis are monolingual: analysis is the same irrespective of the TL; synthesis is the same irrespective of the SL Transfer is bilingual & specific to a particular language-pair e.g., Comprendium MT system SailLabs

18 Direct vs Transfer : how to update a dictionary? Direct: 1 dictionary (e.g., Systran) Ru: { primer example, primery examples} Transfer: 3 dictionaries (e.g., Comprendium) (1)Ru {primery N, plur, nom, lemma=primer} (2)Ru-En {primerexample} (3)En {lemma=example, N, sing example; N, plur examples} 19

Where is the advantage? Direct: 1 dictionary (e.g., Systran) Ru: { primer example, primery examples} Transfer: 3 dictionaries (e.g., Comprendium) (1)Ru {primery N, plur, nom, lemma=primer} (2)Ru-En {primerexample} (3)En {lemma=example, N, sing example; N, plur examples} 20

Multilingual MT: RuEs Direct: 1 dictionary (e.g., Systran) Ru-Es: { primer ejemplo, primery ejemplos} Transfer: 3 dictionaries (e.g., Comprendium) (1)Ru {primery N, plur, nom, lemma=primer} (2)Ru-Es {primerejemplo} (3)Es {lemma=ejemplo, N, sing ejemplo; N, plur ejemplos} 21 Multilingual MT: EnEs Direct: 1 dictionary (e.g., Systran)

En-Es: { example ejemplo, examples ejemplos} Transfer: 3 dictionaries (e.g., Comprendium) (1)En {example N, plur, nom, lemma=example} (2)En-Es {exampleejemplo} (3)Es {lemma=ejemplo, N, sing ejemplo; N, plur ejemplos} 22 The number of modules for a multilingual transfer system n (n 1) transfer modules n (n + 1) modules in total

e.g.: 5-language system (if translates in both directions between all language-pairs) has 20 transfer modules and 30 modules in total (There are more modules than for direct systems, but modules are simpler) 23 Advantages of transfer systems: 1/2 Technical: Analysis and Synthesis modules are reusabile

We separate reusable (transfer-independent) information from language-pair mapping operations performed on higher level of abstraction Challenges: to do as much work as possible in reusable modules of analysis and synthesis to keep transfer modules as simple as possible = "moving towards Interlingua" 24 Advantages of transfer systems: 2/2 Linguistic:

MT can generalise over morphological features, lexemes, tree configurations, functions of word groups MT can access annotated linguistic features for disambiguation 25 Transfer: dealing with lexical and structural mismatch, w.o.: 1/2 Dutch: Jan zwemt English: Jan swims Dutch: Jan zwemt graag English: Jan likes to swim (lit.: Jan swims "pleasurably", with pleasure)

Spanish: Juan suele ir a casa English: Juan usually goes home (lit.: Juan tends to go home, soler (v.) = 'to tend') English: John hammered the metal flat French: Jean a aplati le mtal au marteau Resultative construction in English; French lit.: Jean flattened the metal with a hammer 26 Transfer: dealing with lexical and structural mismatch, w.o.: 2/2

English: The bottle floated past the rock Spanish: La botella pas por la piedra flotando (Spanish lit.: 'The bottle past the rock floating') English: The hotel forbids dogs German: In diesem Hotel sind Hunde verboten (German lit.: Dogs are forbidden in this hotel) English: The trial cannot proceed German: Wir knnen mit dem Proze nicht fortfahren (German lit.: We cannot proceed with the trial) English: This advertisement will sell us a lot German: Mit dieser Anziege verkaufen wir viel (German lit.: With this advertisement we will sell a

lot) 27 Principles of Interface Representations (IRs) IRs should form an adequate basis for transfer, i.e., they should contain enough information to make transfer (a) possible; (b) simple provide sufficient information for synthesis need to combine information of different kinds 1. lematisation 2. freaturisation 3. neutralisation 4. reconstruction

5. disambiguagtion 28 IR features: 1/3 1. lematisation each member of a lexical item is represented in a uniform way, e.g., sing.N., Inf.V. (allows the developers to reduce transfer lexicon) 2. freaturisation only content words are represented in IRs 'as such', function words and morphemes become features on content words (e.g., plur., def., past) inflectional features only occur in IRs if they

have contrastive values (are syntactically or semantically relevant) 29 IR features: 2/3 3. neutralisation neutralising surface differences, e.g., active and passive distinction different word order surface properties are represented as features (e.g., voice = passive) possibly: representing syntactic categories: E.g.: John seems to be rich (logically, John is not a subject of seem): = It seems to someone that John is rich

Mary is believed to be rich = One believes that Mary is rich translating "normalised" structures 30 IR features: 3/3 4. reconstruction to facilitate the transfer, certain aspects that are not overtly present in a sentence should occur in IRs especially, for the transfer to languages, where such elements are obligatory: John tried to leave: S[ try.V John.NP S[ leave.V John.NP]] Vs.: John seems to be leaving 5. disambiguagtion

ambiguities should be resolved at IR: e.g., PP attachment I saw a man with a telescope; a star with a telescope Lexical ambiguities should be annotated: table_1, _2 31 7. Interlingual systems 32 7. Interlingual systems involve just 2 stages: analysis synthesis both are monolingual and independent

there are no bilingual parts to the system at all (no transfer) generation is not straightforward 33 The number of modules in an Interlingual system A system with n languages (which translates in both directions between all language-pairs) requires 2*n modules: 5-language system contains 10 modules 34

Features of Interlingua Each module is more complex Language-independent IR IL based on universal semantics, and not oriented towards any particular family or type of languages IR principles still apply (even more so): Neutralisation must be applied crosslinguistically, no lexical items, just universal semantic primitives: (e.g., kill: [cause[become [dead]]]) 35 From transfer to interlingua

En: Luc seems to be ill Fr: *Luc semble tre malade Fr: Il semble que Luc est malade SEEM-2 (ILL (Luc)) SEMBLER (MALADE (Luc)) Eynde) (Ex.: by F. van Problem: the translation of predicates: Solution: treat predicates as language-specific expressions of universal concepts SHINE = concept-372 SEEM = concept-373 BRILLER = concept-372

SEMBLER = concept-373 36 8. Transfer and Interlingua compared Transfer = translation vs. Interlingual = paraphrase Bilingual contrastive knowledge is central to translation Translators know correct correspondences, e.g., legal terms, where "retelling" is not an option Transfer systems can capture contrastive knowledge IL leaves no place for bilingual knowledge can work only in syntactically and lexically restricted domains

37 Problems with Interlingua 1/2 Semantic differentiation is target-language specific runway startbaan, landingsbaan (landing runway; take-of runway) cousin cousin, cousine (m., f.) No reason in English to consider these words ambiguous making such distinctions is comparable to lexical transfer

not all distinctions needed for translation are motivated monolingually: no "universal semantic features 38 Problems with Interlingua 2/2: Result: Adding a new language requires changing all other modules exactly what we tried to avoid Interlingua doesnt work: why? Sapir-Whorf Hypothesis: can this be an explanation? There is no universal language of thought The way how we think / perceive the world is

determined by our language We can put off spectacles of language only by putting on other spectacles of another language 39 Transfer vs. Interlingua Transfer has a theoretical background, it is not an engineering ad-hoc solution, a "poor substitute for Interlingua". It must be takes seriously and developed through solving problems in contrastive linguistics and in knowledge representation appropriate for translation tasks". Whitelock and Kilby, 1995, p. 7-9

40 MT architectures: open questions Depth of the SL analysis Nature of the interface representation (syntactic, semantic, both?) Size and complexity of components depending how far up the MT triangle they fall Nature of transfer may be influenced by how typologically similar the languages involved are the more different -- the more complex is the transfer

41 What are the limits of MT architectures ? English: 10 pounds will buy you decent milk (translate into German, Russian, Japanese) (English has fewer constraints on subjects) English: "to call a spade a spade" English: "to kick the bucket" is there something that cannot be translate in principle? 42

Principal challenge: Meaning is not explicitly present "The meaning that a word, a phrase, or a sentence conveys is determined not just by itself, but by other parts of the text, both preceding and following The meaning of a text as a whole is not determined by the words, phrases and sentences that make it up, but by the situation in which it is used". M.Kay et. al.: Verbmobil, CSLI 1994, pp. 11-1 43 9. Limitations of the stateof-the-art MT

architectures Q.: are there any features in human translation which cannot be modelled in principle (e.g., even if dictionary and grammar are complete and perfect)? MT architectures are based on searching databases of translation equivalents, cannot invent novel strategies add / removing information prioritise translation equivalents trade-off between fluency and adequacy of translation 44 Problem 1: Obligatory loss of

information: negative equivalents ORI: His pace and attacking verve saw him impress in Englands game against Samoa HUM: HUM: His pace and attacking power impressed during the game of England with Samoa ORI: Legouts verve saw him past world No 9 Kim Taek HUM: , 9- HUM: Legouts persistency allowed him to get

round Kim Taek 45 Problem 2: Information redundancy Source Text and the Target Text usually are not equally informative: Redundancy in the ST: some information is not relevant for communication and may be ignored Redundancy in the TT: some new information has to be introduced (explicated) to make the TT well-formed e.g.: MT translating etymology of proper names, which is redundant for communication :

Bill Fisher => to send a bill to a fisher 46 Problem 3: changing priorities dynamically (1/2) Salvadoran President-elect Alfredo Christiani condemned the terrorist killing of Attorney General Roberto Garcia Alvarado SYSTRAN: MT: Garcia Alvarado MT(lit.) Salvadoran elected president Alfredo Christiani condemned the killing

of a terrorist Attorney General Roberto Garcia Alvarado 47 Problem 3: changing priorities dynamically (2/2) PROMT However: Who is working for the police on a terrorist killing mission?

, ? Lit.: Who works for police on a terrorist, killing the mission? 48 Fundamental limits of stateof-the-art MT technology (1/2) Wide-coverage industrial systems: There is a competition between translation equivalents for text segments MT: Order of application of equivalents is fixed Human translators able to assess relevance and re-arrange the order An MT system can be designed to translate

any sentence into any language However, then we can always construct another sentence which will be translated wrongly 49 Fundamental limits of stateof-the-art MT technology (2/2) Correcting wrong translation: terrorist killing of Attorney General = killing of a terrorist (presumably, by analogy to tourist killing or farmer killing); not killing by terrorists = Introducing new errors just pretending to be a terrorist killing war

machine who is working for the police on a terrorist killing mission merged into the "TKA" (Terrorist Killing Agency), they would proceed to wherever terrorists operate and kill them, 50 Translation: As true as possible, as free as necessary [] a German maxim so treu wie mglich, so frei wie ntig (as true as possible, as free as necessary) reflects the logic of translators decisions well: aiming at precision when this is possible, the translation allows liberty only if

necessary [] The decisions taken by a translator often have the nature of a compromise, [] in the process of translation a translator often has to take certain losses. [] It follows that the requirement of adequacy has not a maximal, but an optimal nature. (Shveitser, 1988) 51 10. MT and human understanding Cases of contrary to the fact translation ORI: Swedish playmaker scored a hat-trick in the 4-2 defeat of Heusden-Zolder MT: - 4-2 Heusden-Zolder.

(Swedish playmaker won a hat-trick in this defeat 4-2 Heusden-Zolder) In English the defeat may be used with opposite meanings, needs disambiguation: Xs defeat == Xs loss Xs defeat of Y == Xs victory 52 Why we need human or artificial intelligence in translation

Xs defeat == Xs loss Xs defeat of Y == Xs victory ORI: Swedish playmaker scored a hat-trick in the 4-2 defeat of Heusden-Zolder Vs its defeat of last night their FA Cup defeat of last season their defeat of last seasons Cup winners last seasons defeat of Durham 53 MT and human understanding

MT is just an expert system without real understanding of a text What is real understanding then? Can the understanding be precisely defined and simulated on computers? 54

Recently Viewed Presentations


    Authentication & Authorization of SharePoint IIS and SmartCards Implementation Considerations and Pitfalls Dan Usher MCP, MCTS, Security+ SharePoint Architect and Implementation / Deployment Engineer UVA - BS Physics Joel Ward MCP, MCAD Solutions Developer and Architect Penn State - BA...
  • Poetry Part II: Modernism & Post-Modernism 20th Century

    Poetry Part II: Modernism & Post-Modernism 20th Century

    Poetry Part II: Modernism & Post-Modernism 20th Century Anglo-Americans 20th century Women Writers 20th century African American Writers 20th century Latin American Writers
  • Chapter 8

    Chapter 8

    Chapter 8: Manipulating Strings Programming with Microsoft Visual Basic 2005, Third Edition * * * * * * * * * * * * * * * * * * * * * * * * * * Programming with...
  • Accessibility Solutions in a Digital ... - Quality Matters

    Accessibility Solutions in a Digital ... - Quality Matters

    Accessibility Basics. Accessible design is a design process in which the needs of people with disabilities are specifically considered. Web accessibility refers to the inclusive practice of removing barriers that prevent interaction with, or access to websites, by individuals with...
  • Wollondilly Health Alliance

    Wollondilly Health Alliance

    Finds it easier and quicker to access services. Has access to the highest quality of health services. Has a say in the development and provision of health services that affect them. What is the Alliance? As the name alludes, it...
  • Indian Culture and Music 2008 Fulbright Summer Seminar

    Indian Culture and Music 2008 Fulbright Summer Seminar

    Indian Culture and Music 2008 Fulbright Summer Seminar to India & Sri Lanka India-South Asian Adventure! "Unity through diversity" is the theme of the approximately one billion people that live in a country that is so big, it's called a...
  • System of Care

    System of Care

    Provides incentives for community to engineer enduring positive change by: Increasing school attendance and performance. Decreasing instances of abuse, neglect, juvenile just involvement. Increasing family involvement and satisfaction in meeting the behavioral, mental, physical, education and safety needs of their...
  • Beyond Traffic: The Smart City Challenge Information Session ...

    Beyond Traffic: The Smart City Challenge Information Session ...

    Encourage cities to put forward their best and most creative ideas for innovatively addressing the challenges they arefacing. The Smart City Challenge will address how emerging transportation data, technologies, and applications canbe integrated with existing systems in a city to...