Transcript Slide 1
Disambiguation of homographic adjective
and adverb forms in Croatian texts
Danijela Merkler*, Daša Berović*, Željko Agić**
* Department of Linguistics
** Department of Information Sciences
Faculty of Humanities and Social Sciences, University of Zagreb
[email protected]; [email protected]; [email protected]
NooJ 2011
Dubrovnik
2011-06-15
Talk overview
NooJ2011
Dubrovnik
2011-06-15
project ACCURAT
problem and corpora
modeling local grammars and applying them
statistical evaluation
ACCURAT
FP7 project
main goal - to develop methods and techniques to
overcome one of the central problems of machine
translation – the lack of linguistic resources for underresourced areas of machine translation
key innovation - creation of methodology and tools to
measure, to find and to use comparable corpora to
improve the quality of MT
the ACCURAT project will significantly contribute not
only to the theory of MT, but also to corpus linguistics,
information extraction and natural language
processing in general
NooJ2011
Dubrovnik
2011-06-15
Scientific objectives
create comparability metrics – to develop the
methodology and determine criteria to measure the
comparability of source and target language
documents in comparable corpora
establish research methods for alignment and
extraction of lexical, terminological and other
linguistic data from comparable corpora
disambiguation – important process for POS and MSD
tagging
NooJ2011
Dubrovnik
2011-06-15
Problem
parallel and comparable resources are sparse for Croatian
when paired with any of the languages included in the
project, especially if the other language is under-resourced
as well
importance of high quality annotation for existing language
resources for Croatian
building (factored) language models for MT
using text anchors in comparable resources
MSD-tagging and lemmatization errors detected in existing
Croatian language resources
NooJ2011
Dubrovnik
2011-06-15
e.g. Croatian National Corpus v2.5 (automatically lemmatized
and MSD-tagged), manually annotated subcorpora, Croatian
Dependency Treebank
manual analysis of their annotation reveals regular patterns in
these errors
Problem
forms of descriptive adjectives in the nominative singular case in
the neuter gender are the same as the forms of the adverbs that
are made from those adjectives by suffixation
these adverbs are realized in context
in most cases adverb is made from adjective that has abstract
meaning
there are several types of word forms
NooJ2011
Dubrovnik
2011-06-15
the forms of adverbs and adjectives that occur with
no semantic constraints: razdragano (gleeful), bahato (arrogant),
ubrzano (rapidly), uzrujano (upset), umiljato (cuddly)
forms that are made from verbs: drhtavo (shaking), laskavo
(flattering), šepavo (lame)
forms that have dual meaning (concrete and abstract): mlako
(lukewarm), šugavo (itchy), mračno (darkly), hladno (cold), gorko
(bitter)
forms that denote spatial and temporal relations: rano (early),
duboko (deeply), plitko (shallow), lijevo (left)
Corpora
Croatia Weekly
100 kw newspaper corpus (newspaper published from
1998 to 2000, 118 numbers)
it covers different domains: politics, economy and
finance, tourism, ecology, culture, art, sports
part of Croatian side of the Croatian-English Parallel
Corpus manually lemmatized and MSD-tagged using the
MULTEXT-East v3 morphosyntactic specifications
1984.
Orwell’s "1984" corpus, manually lemmatized and MSDtagged using MULTEXT-East v4
languages: En, Ro, Sl, Cs, Et, Hu, Sr, Bg, Ru, Mk, Hr...
encoded in TEI P4 (XML)
NooJ2011
Dubrovnik
2011-06-15
Corpora
imported the corpora to NooJ
used the NooJ XML import feature
kept the MSD feature annotations for adjectives,
adverbs, nouns and verbs
converted the annotations for these PoS from MultextEast to NooJ format for lexical resources
modified feature annotations
e.g. MTE verb type from auxiliary, copulative to PG
(auxiliary verb) in NooJ
preprocessing enabled designing the rules without
using Croatian resources for NooJ, i.e. skipping NooJ
linguistic analysis
NooJ2011
Dubrovnik
2011-06-15
Patterns
we noticed several types of patterns in which adverbs
that are homographic with adjectives occur
they are defined by their contextual environment
1) Vpg + A* + V → Vpg + R* + V
2) Vpg + A + A* → Vpg + R + A*
3) A* + V → R* + V
4) A + A* + N → R + A* + N
NooJ2011
Dubrovnik
2011-06-15
Vpg + A* + V
NooJ2011
Dubrovnik
2011-06-15
Vpg + A + A*
NooJ2011
Dubrovnik
2011-06-15
A* + V
NooJ2011
Dubrovnik
2011-06-15
A + A* + N
NooJ2011
Dubrovnik
2011-06-15
Statistics 1
manually checked concordances
cw100
orwell
cw100 + orwell
Vpg + A* + V
64 %
62 %
63 %
Vpg + A + A*
100 %
100 %
100 %
A* + V
82 %
54 %
67 %
A + A* + N
69 %
75 %
70 %
total
77 %
61 %
70 %
errors frequently include the word sve, so we
upgraded all grammars in order not to recognize sve
NooJ2011
Dubrovnik
2011-06-15
Example of upgraded grammar
NooJ2011
Dubrovnik
2011-06-15
Statistics 2
cw100
orwell
cw100 + orwell
Vpg + A* + V
100 %
83 %
92 %
Vpg + A + A*
100 %
100 %
100 %
A* + V
87 %
63 %
74 %
A + A* + N
78 %
100 %
82 %
total
89 %
73 %
83 %
obtained results improved after we applied new
grammars
significant difference between newspaper and
literature corpus
NooJ2011
Dubrovnik
2011-06-15
Future work
forms of relational adjectives in the nominative
singular case in the masculine gender are the same as
the forms of the adverbs that are made from those
adjectives by suffixation (junački, pučki, bratski,
životinjski)
disambiguation of these forms also depends
on the grammatical context in which they occur, so it
can also be done in a similar way
applying the disambiguation rules to other Croatian
language resources
NooJ2011
Dubrovnik
2011-06-15
Thank you for your attention.
www.accurat-project.eu
The research within the project Accurat leading to
these results has received funding from the European
Union Seventh Framework Programme (FP7/20072013), grant agreement no 248347.