A case study on supervised classification of Swedish pseudo-coordination
Malin Ahlberg, Peter Andersson, Markus Forsberg, Nina Tahmasebi · DSpace repository (University of Tartu) · 2015
We present a case study on supervised classification of Swedish pseudocoordination (SPC).The classification is attempted on the type-level with data collected from two data sets: a blog corpus and a fiction corpus.Two small experiments were designed to evaluate the feasability of this task.The first experiment explored a classifier's ability to discriminate pseudo-coordinations from ordinary verb coordinations, given a small labeled data set created during the experiment.The second experiment evaluated how well the classifier performed at detecting and ranking SPCs in a set of unlabeled verb coordinations, to investigate if it could be used as a semi-automatic discovery procedure to find new SPCs.1.It is possible to front an object or bound adverbial of V 2 that is not compatible with V 1 : Hon satt och skrev en bok.'She sat and wrote a book.' ⇒ Det var en bok som hon satt och skrev.'It was a book that she sat and wrote.' 2. The order of V 1 and V 2 is fixed: Mona satt och skrev 'Mona sat and wrote.' ⇒ ?Mona skrev och satt.'Mona wrote and sat' 3. Some paraphrasings are blocked: Mona satt och sydde 'Mona sat and sewed.' ⇒ ?Mona satt och hon sydde.'Mona sat and she sewed' 4. både V 1 och V 2 'both V 1 and V 2 ' is blocked: ?Mona både satt och sydde 'Mona both sat and sewed.' 5.There are usually no or few arguments between V 1 and och.