Orð og tunga - 01.06.2006, Page 145

Þórdís Úlfarsdóttir: Málfræðileg mörkun orðasambanda
143
Jón Hilmar Jónsson. 2001. Orðastaður (2. útgáfa). Reykjavík: JPV.
Jörgen Pind (ritstj.), Friðrik Magnússon og Stefán Briem. 1991. íslensk
orðtíðnibók. Reykjavík: Orðabók Háskólans.
Kristín Bjarnadóttir. 2004. Beygingarlýsing íslensks nútímamáls. í:
Samspil tungu og tækni. Afrakstur tungutækniverkefnis menntamdla-
ráðuneytisins. Bls. 23-25.
Sigrún Helgadóttir. 2004a. Markari fyrir íslenska texta. í: Samspil tungu
og tækni. Afrakstur tungutækniverkefnis menntamálaráðuneytisins. Bls.
55-64.
Sigrún Helgadóttir. 2004b. Mörkuð íslensk málheild. í: Samspil tungu
og tækni. Afrakstur tungutækniverkefnis menntamálaráðuneytisins. Bls.
65-71.
Sigrún Helgadóttir. 2005. Testing Data-Driven Learning Algorithms
for PoS Tagging of Icelandic. í: Nordisk Sprogteknologi 2004 - Nordic
Language Technology. BIs. 257-265.
Heimildir á vefnum
Orðasambandaskrá Orðabókar Háskólans: www.lexis.hi.is/osamb/
osamb.pl
Upplýsingar um Orðasambandaskrá Orðabókar Háskólans: www.lex-
is.hi.is/osamb/info.pl
Abstract
The topic of this article is the electronic tagging of phrases, fixed ex-
pressions and idioms as foimd in the collection of Orðabók Háskólans
(Institute of Lexicography). The tool used for this, called TnT-tagger,
grammatically analyses the words contained within the phrases. For
this experiment, ca. 200 phrases were used, centred on two verbs (afla
and aka) and two adjectives (feitur and glaður). The tagging process is
described as well as the outcome of the tagging and the errors which
occurred. The results are measured. The experiment also includes the
tagging of several definitions from a dictionary (íslensk orðabók). It is
shown how the tags produced can be used for sorting the phrases so
that they fall into groups of syntactic pattems. It is argued that this
method is useful for finding patterns in the syntax of the keywords in
question and for evaluating the frequency of various constructions.