Machine Translation Challenges and Language DivergencesMajor Sources of Translation ProblemsLexical DifferencesGoogle at Work…Slide 5Slide 6Slide 7Slide 8MT Handling of Lexical DifferencesStructural DifferencesSlide 11Slide 12Slide 13MT Handling of Structural DifferencesSyntax-to-Semantics DifferencesSlide 16Slide 17Slide 18Slide 19Slide 20Slide 21Slide 22Slide 23Same intention, different syntaxMT Handling of Syntax-to-Semantics DifferencesIdioms and ConstructionsSlide 27Formulaic UtterancesConstructionsSlide 30MT Handling of Constructions and IdiomsTake Home MessagesSummaryHomework Assignment #1Questions…Machine TranslationChallenges and Language DivergencesAlon LavieLanguage Technologies InstituteCarnegie Mellon University11-731: Machine TranslationJanuary 12, 2011January 12, 2011Major 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 Constructions211-731: Machine TranslationJanuary 12, 2011Lexical 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)311-731: Machine TranslationJanuary 12, 2011Google at Work…411-731: Machine TranslationJanuary 12, 2011 511-731: Machine TranslationJanuary 12, 2011 611-731: Machine TranslationJanuary 12, 2011Lexical Differences•Lexical gaps: –Examples: these have no direct equivalent in English:gratiner(v., French, “to cook with a cheese coating”)ōtosanrin(n., Japanese, “three-wheeled truck or van”)711-731: Machine TranslationJanuary 12, 2011[From Hutchins & Somers]Lexical Differences811-731: Machine TranslationJanuary 12, 2011MT Handling of Lexical Differences•Direct MT and Syntactic Transfer:–Lexical Transfer stage uses bilingual lexicon–SL word can have multiple translation entries, possibly augmented with disambiguation features or probabilities–Lexical Transfer can involve use of limited context (on SL side, TL side, or both)–Lexical Gaps can partly be addressed via phrasal lexicons•Semantic Transfer:–Ambiguity of SL word must be resolved during analysis  correct symbolic representation at semantic level–TL Generation must select appropriate word or structure for correctly conveying the concept in TL 911-731: Machine TranslationJanuary 12, 2011Structural 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)1011-731: Machine TranslationJanuary 12, 2011 1111-731: Machine TranslationJanuary 12, 2011 1211-731: Machine TranslationJanuary 12, 2011 1311-731: Machine TranslationJanuary 12, 2011MT Handling of Structural Differences•Direct MT Approaches:–No explicit treatment: Phrasal Lexicons and sentence level matches or templates•Syntactic Transfer:–Structural Transfer Grammars•Trigger rule by matching against syntactic structure on SL side•Rule specifies how to reorder and re-structure the syntactic constituents to reflect syntax of TL side•Semantic Transfer:–SL Semantic Representation abstracts away from SL syntax to functional roles  done during analysis–TL Generation maps semantic structures to correct TL syntax1411-731: Machine TranslationJanuary 12, 2011Syntax-to-Semantics Differences•Meaning in TL is conveyed using a different syntactic structure than in the SL–Changes in verb and its arguments–Passive constructions–Motion verbs and state verbs–Case creation and case absorption•Main Distinction from Structural Differences:–Structural differences are mostly independent of lexical choices and their semantic meaning  addressed by transfer rules that are syntactic in nature–Syntax-to-semantic mapping differences are meaning-specific: require the presence of specific words (and meanings) in the SL 1511-731: Machine TranslationJanuary 12, 2011Syntax-to-Semantics Differences•Structure-change example:I like swimming“Ich scwhimme gern”I swim gladly1611-731: Machine TranslationJanuary 12, 2011 1711-731: Machine TranslationJanuary 12, 2011Syntax-to-Semantics Differences•Verb-argument example:Jones likes the film.“Le film plait à Jones.”(lit: “the film pleases to Jones”)•Use of case roles can eliminate the need for this type of transfer – Jones = Experiencer– film = Theme1811-731: Machine TranslationJanuary 12, 2011 1911-731: Machine TranslationJanuary 12, 2011 2011-731: Machine TranslationJanuary 12, 2011Syntax-to-Semantics Differences•Passive Constructions•Example: French reflexive passives:Ces livres se lisent facilement*”These books read themselves easily”These books are easily read2111-731: Machine TranslationJanuary 12, 2011 2211-731: Machine TranslationJanuary 12, 2011 2311-731: Machine TranslationJanuary 12, 2011Same intention, different syntax•rigly bitiwgacny my leg hurts•candy wagac fE rigly I have pain in my leg•rigly bitiClimny my leg hurts•fE wagac fE rigly there is pain in my leg•rigly bitinqaH calya my leg bothers on meRomanization of Arabic from CallHome Egypt.2411-731: Machine TranslationJanuary 12, 2011MT Handling of Syntax-to-Semantics Differences•Direct MT Approaches:–No Explicit treatment: Phrasal Lexicons and sentence level matches or templates•Syntactic Transfer:–“Lexicalized” Structural Transfer Grammars•Trigger rule by matching against “lexicalized” syntactic structure on SL side: