NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković,...

22
NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty of Humanities and Social Science {kvuckovi, bbekavac,zdovedan}@ffzg.hr NooJ2009 Tozeur 2009-06-09

Transcript of NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković,...

Page 1: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 1/22

SynCro - Parsing Simple Croatian Sentences

Kristina Vučković, Božo Bekavac, Zdravko DovedanUniversity of Zagreb, Faculty of Humanities and Social Science

{kvuckovi, bbekavac,zdovedan}@ffzg.hr

NooJ2009Tozeur

2009-06-09

Page 2: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 2/22

Overview of the work

on our way to complete parse trees for Croatian sentences building partial trees for simple Croatian

sentences favor of precision over recall

Building syntactic parse trees for Croatian is quite a challenge!

properties of Croatian language: mostly free word (better to say

constituent?) order → scrambling very frequent

could be a long distance between parts of predicate

Page 3: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 3/22

Syntactic trees

at this stage, the following structures of parse trees are described verb subject - verb subject - verb - direct object subject - verb - direct (and, or indirect

object) in addition to all these combinations, we

can detect adverbial phrases of place and adverbial phrases of time (temporal

expressions) Complex combinations (e.g. multiple PPs)

are not described

Page 4: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 4/22

Sentance structure in Croatian

<subject> <predicate> <object_D> <object_ID> <A_place><A_time><predicate>

<predicate>

<subject>

<subject>

Page 5: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 5/22

Recognition of: predicate node

Page 6: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 6/22

Recognition of: subject node

Page 7: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 7/22

Recognition of: direct object node

Page 8: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 8/22

Recognition of: indirect object node

Page 9: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 9/22

Recognition of: Adverbs of Time

Page 10: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 10/22

Recognition of: Adverbs of Place

Page 11: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 11/22

Exampless

Page 12: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 12/22

Exampless

Page 13: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 13/22

Exampless

Page 14: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 14/22

Exampless

Page 15: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 15/22

Exampless

Page 16: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 16/22

Exampless

dislocated predicate <PRED>

Page 17: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 17/22

Exampless

dislocated predicate <PRED>

Page 18: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 18/22

Exampless

dislocated predicate <PRED>

Page 19: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 19/22

Exampless

dislocated predicate <PRED> and dislocated subject <SUB>

Page 20: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 20/22

Addition to the Lexicon

For recognizing Adverbials of Time and Place:

Adjectives +time / + place R+vr R+mt

Prepositions +time / + place S+vr S+mt

Page 21: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 21/22

Problems

if there is a nominal predicate

if the <NP> node is a coordination made of 2 or more <NP>’s of different gender

if <S> has more than one annotation

ex. The child was very

smart.

-> The child was->was very smart. ex. The boy and a girl were

very smart.

->The boy and a girl =><NP+p+m> ex.

He was singing from March to April.

He was singing from Paris to Tozeur.

and Future Work

Page 22: NooJ2009 Tozeur 2009-06-09 1/22 SynCro - Parsing Simple Croatian Sentences Kristina Vučković, Božo Bekavac, Zdravko Dovedan University of Zagreb, Faculty.

NooJ2009Tozeur2009-06-09 22/22