Motivations for transfer-based translation

• lexical ambiguity

• structural differences

See further Ingo 91

Example 1

Sv. Fyll på olja i växellådan. En. Fill gearbox with oil.(from the Scania corpus)

• fyll på fill

• obj adv

• adv obj

Example 2

Sv. I oljefilterhållaren sitter en överströmningsventil.

En. The oil filter retainer has an overflow valve.(from the Scania corpus)

• sitter has• adv subj• subj obj

Transfer-based translation

• intermediary sentence structure• basic processes

– analysis– transfer– generation (synthesis)

• language modules– dictionary and grammar of SL– transfer dictionary and transfer rules– dictionary and grammar of TL

SL TL

Interlingua

Direct translation

Transfer

Multra

Metal

Levels of intermediary structure

• cf. J&M, Chapter 21

• word order

Metal

• See H&S

MULTRA

Multilingual Support for Translation and Writing• translation engine• transfer-based

– shake-and-bake

• modular• unification-based• preference machinery• trace-able

Analysis

• chart parser (Lisp C)– procedural formalism

• unification and other kinds of operations

• sentence structure– feature structure– grammatical relations– surface order implicit via grammatical relations

See further Sågvall Hein&Starbäck (99),Weijnitz (02), Dahllöf (89)

Transfer

• unification-based• declarative formalism

– Multra transfer formalism (Beskow 93) • lexical and structural rules

• rules are partially ordered• a more specific rule takes precedence over a

less specific one– specificity in terms of number of transfer equations

• all applicable rules are applied• written in prolog

Generation

• syntactic generation– Multra syntactic generation formalism (Beskow 97a)– PATR-like style

• unification• concatenation• typed features

• morphological generation (Beskow 97b)– lexical insertion rules– morphological realisation and phonological finish in

prolog

• written in prolog

An example: Tippa hytten.Tippa hytten. :

(* = (PHR.CAT = CL MODE = IMP

SUBJ = 2ND VERB = (WORD.CAT = VERB INFF = IMP DIAT = ACT LEX = TIPPA.VB.1

VSURF = +) OBJ.DIR = (PHR.CAT = NP NUMB = SING GENDER = UTR CASE = BASIC DEF = DEF HEAD = (LEX = HYTT.NN.1 WORD.CAT = NOUN))) REG = (V1.LEM = TIPPA.VB) SEP = (WORD.CAT = SEP LEX = STOP.SR.0)))

Transfer structureTransfer structure

[VERB : [WORD.CAT : VERB LEX : TILT.VB.0 DIAT : ACT INFF : IMP] OBJ.DIR : [PHR.CAT : NP DEF : DEF NUMB : SING HEAD : [WORD.CAT : NOUN LEX : CAB.NN.0]] MODE : IMP SUBJ: 2ND VSURF: + SEP : [WORD.CAT : SEP LEX : STOP.SR.0] PHR.CAT : CL]

Generation

Tilt the cab.  

A grammar rule

defrule legal.obj {<?1 phr.cat> = 'np,not <?1 case> = 'gen, not <?1 case> = 'subj

}

Transfer rules

• copy feature

• delete feature

• transfer feature

• assign feature

Copy feature

LABEL modeSOURCE <* mode> = ?x1TARGET <* mode> = ?x2TRANSFER

Delete feature

LABEL REGSOURCE <* REG> = ANYTARGET <*> = <*> TRANSFER

Transfer feature

LABEL OBJ.DIRSOURCE <* OBJ.DIR> = ?x1TARGET <* OBJ.DIR> = ?x2TRANSFER ?x1 <=> ?x2 

Define feature

LABEL trycka.in-pressSOURCE <* lex sym>=trycka.vb+in.ab.1 <* word.cat>=VERBTARGET <* lex>=press.vb.1 <* word.cat>=VERBTRANSFER

 

A generation rule

LABEL CL.IMPX1 ---> X2 X3 X4 : <X1 PHR.CAT> = CL <X1 VERB> = <X2> <X1 TYPE> = IMP <X1 OBJ.DIR> = <X3> <X1 SEP> = <X4>

A contextual lexical ruleLABEL tänka.på-think.aboutSOURCE <* verb lex sym> = tänka.vb.1 <* obj.prep phr.cat> = pp <* obj.prep prep> = ?prep <* obj.prep prep lex sym> = på.pp.1 <* obj.prep rect> = ?rect1TARGET <* obj.prep phr.cat> = pp <* obj.prep prep word.cat> = PREP <* obj.prep prep lex> = about.pp.1 <* obj.prep rect> = ?rect2TRANSFER ?rect1<=>?rect2

 

A generation trace

1-Applying Rule cl-sep

1- Applying Rule cl.imp

1- Applying Rule subj2nd-verb-obj.dir

1- Applying Rule verb.main.act

1- Applying Rule np.the-df

1- Applying Rule ng.noun-def

1-Success!

Language resources in the MATS system

• dictionary in a database with different views

• analysis grammar

• transfer grammar– incl. contextually defined lexical rules

• generation grammar

sv-en_LinkLexicon

en-Inflections

en_LemmaLexicon

en_LexemeLexicon

en_Lexicon

en_StemLexicon

sv_Inflections

sv_LemmaLexicon

sv_LexemeLexicon

sv_Lexicon

sv_StemLexicon

The MATS system

Frozen demo…

Assignment 2: Working with MATS

http://stp.ling.uu.se/~evapet/mt04/assignment2.html

Lexicalistic translation

• Identify (lexical) translation units in the source sentence

• Translate each unit separately (considering the context)

• Order the result in agreement with a model of the target language

Formulation due to Lars Ahrenberg; see further AH (reading list) ; see also Beaven, L. John, Shake-and-Bake Machine Translation. Coling –92, Nantes, 23-28 Aout 1992.

T4F – a lexicalistic system

• processes in T4F– tokenisation– tagging– transfer– transposition– filtering

See further AH (in the reading list)

Interlingua translation

• See SN

Applications of alignment

• translation memories

• translation dictionaries

• lexicalistic translation

• statistical machine translation

• example-based translation

Translation memories

• based on sentence links

• optionally, sub sentence links

See further Macklovitch, E. (2000)

Translation dictionaries

• based on word links

• refinement of word links

Refinement of word alignment data

• neutralise capital letters where appropriate• lemmatise or tag source and target units• identify ambiguities

– search for criteria to resolve them

• identify partial links– compounds?– remove or complete them

• manual revision?

Informally about statistical MT

• build a translation dictionary based on word alignment

• aim for as big fragments as possible• keep information on link frequency• build an n-gram model of the target language• implement a direct translation strategy

– including alternatives ordered by length and frequency

• process the output by the n-gram model filtering out the best alternatives and adjust the translation accordingly

Example-based MT

HS (in the reading list)

Some current research topics

• intersentential dependences• hybrid systems: data-driven and rule-driven• improved alignment techniques• improved language modeling in ST• automatic learning from post-editing• translation by structural correspondences• translation of spoken language• improved preference strategies• ambiguity preserving translation

Intersentential dependencies

• pronoun resolution

• lexical ambiguity resolution, such as– (torkar)motorn the motor– (förbrännings)motorn the engine

• fluency

Preserving the information structure

• information structure is expressed in different ways in the source and the target

• syntactic clues are exploited in the analysis to compute the information structure (topic-focus articulation)

• information structure is used to guide the generation

An example

Torkarmotorn M2 är sammankopplad med omkopplare S24 och intervallrelä R22. För att inte motorn skall överbelastas, t.ex. om torkarbladen fastnat, finns en inbyggd termovakt som bryter strömmen till motorn när …

Wiper motor M2 is connected to switch S24 and intermittent relay R22. To prevent motor overload, e.g. if the wiper blade gets stuck, there is an integral thermal sensor which breaks the current to the motor when …

Preferences

• syntactic preferences– the principle of right association– the principle of minimal attachment– two-stage processing

• semantic preferences– lexical selectional restrictions– lexical contextual rules– conceptual taxonomies– likelihood of occurrence

See further Bennet, P. & Paggio, P., 1993, Preference in Eurotra.

Preferences in Multra

• parsing– a formalism for expressing syntactic

preferences in the parse• not fully developed

• transfer– contextual lexical rules– rule specificity

• generation– rule specificity

Hybrid systems

• aims

• components

• problems

• architecture

• scores

Aims of a hybrid system

• simple techniques for simple tasks

• complex techniques for complex tasks

Components of a hybrid systems

• component strategies– translation memory

• full sentences• fragments

• direct translation– statistical translation– ebmt

Component strategies, cont’d

• rule-based translation– simplistic analysis (cf. direct translation)

• word by word (S sequence of words)• phrase by phrase (S sequence of phrases)

– partial parsing– full parsing

Problems of a hybrid system

• how does the system know when a simple technique is appropriate?– does the source tell?– does the target tell?

Architecture and scores

• simple first?

• concerting results?

• scoring?

Improved techniques for re-use of translation

• combining clues for word alignment (Tiedemann 2003)

• interactive word alignment (Ahrenberg et al. 2003)

• parallel treebanks

Translation by structural correspondences

• LFG

• HPSG

Translation of spoken language

See

Krauver, Steven (ed.), 2000, Machine Translation, June 2000. Volume 15, Issue 1-2, Special issue on Spoken Language Translation.