Statistical Machine Translation with Rule Based Re-ordering of Source Sentences Amit Sangodkar
Vasudevan N
Om P. Damani
(CSE, IIT Bombay)
Statistical Machine Translation with Rule Based Re-ordering of Source Sentences Amit Sangodkar
Vasudevan N
Om P. Damani
(CSE, IIT Bombay)
Motivation
Combining Linguistic knowledge with Statistical Machine Translation.
Can re-ordering source language sentences as per target language improve the alignment?
Example
English: Many Bengali poets have sung songs in praise of this land.
Hindi: कई बंगाली कवियों ने इस महान भूमि की प्रशंसा के गीत गाए हैं
Re-order: Many Bengali poets this land of praise in songs sung have
Translation Architecture
Dependency Parser
Many Bengali poets have sung songs in praise of this land.
amod (poets-3, Many-1)
nn (poets-3, Bengali-2)
nsubj (sung-5, poets-3)
aux (sung-5, have-4)
dobj (sung-5, songs-6)
prep_in (sung-5, praise-8)
det (land-11, this-10)
prep_of (praise-8, land-11)
------------------------------------
Output of Stanford Parser
Tree Processing
Handling Auxiliary Verbs
remove and postfix to their respective verb
e.g. aux(sung, have) sung_have
Handling Prepositions/Conjunctions
extract the preposition from the relation and attach to parent/child
e.g. prep_in(sung, praise) prep(sung, praise_in)
Modified Dependency Tree
Re-ordering
Parent-Child Positioning
Prioritizing the Relations
Re-ordering (Parent-Child Positioning)
parent before child conj (conjunction), appos (apposition), advcl (adverbial clause), ccomp (clausal complement), rcmod (relative clause modifier)
e.g. John cried because he fell
advcl(cry, fell). In Hindi, cry is ordered before fell.
child before parent nsubj(subject), dobj(object)
e.g. Ram eats mango
dobj(eat,mango). In Hindi, mango ordered before eat.
Re-ordering (Relation Priority)
- R R - - nn L - R - - amod L L - L R prep - - R - R dobj - - L L - nsubj nn amod prep dobj nsubj Deciding the order in case of multiple children
Priority among relation pairs
Illustration - Re-ordering
sung_have poets praise_in songs land_of this Many Bengali nsubj prep dobj amod nn prep det - L R prep R - R dobj L L - nsubj prep dobj nsubj Input Dependency Tree
Illustration - Re-ordering
sung_have poets praise_in songs land_of this Many Bengali nsubj prep dobj amod nn prep det
Illustration - Re-ordering
sung_have poets praise_in songs land_of this Many Bengali nsubj prep dobj amod nn prep det - R nn L - amod nn amod
Illustration - Re-ordering
sung_have poets praise_in songs land_of this Many Bengali nsubj prep dobj amod nn prep det
Output: Many
Illustration - Re-ordering
sung_have poets praise_in songs land_of this Many Bengali nsubj prep dobj amod nn prep det
Output: Many
Illustration - Re-ordering
sung_have poets praise_in songs land_of this Many Bengali nsubj prep dobj amod nn prep det
Output: Many Bengali
Illustration - Re-ordering
sung_have poets praise_in songs land_of this Many Bengali nsubj prep dobj amod nn prep det
Output: Many Bengali poets
Illustration - Re-ordering
sung_have poets praise_in songs land_of this Many Bengali nsubj prep dobj amod nn prep det - L R prep R - R dobj L L - nsubj prep dobj nsubj
Output: Many Bengali poets
Illustration - Re-ordering
sung_have poets praise_in songs land_of this Many Bengali nsubj prep dobj amod nn prep det
Output: Many Bengali poets this
Illustration - Re-ordering
sung_have poets praise_in songs land_of this Many Bengali nsubj prep dobj amod nn prep det
Output: Many Bengali poets this land of
Comments