Detail publikace

A New Approach to Pseudoword Generation

OTRUSINA, L. SMRŽ, P.

Originální název

A New Approach to Pseudoword Generation

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

Sense-tagged corpora are used to evaluate word sense disambiguation (WSD)systems. Manual creation of such resources is often prohibitively expensive.That is why the concept of pseudowords - conflations of two or moreunambiguous words - has been integrated into WSD evaluation experiments. Thispaper presents a new method of pseudoword generation which takes into accountsemantic-relatedness of the candidate words forming parts of the pseudowords tothe particular senses of the word to be disambiguated. We compare the newapproach to its alternatives and show that the results on pseudowords, that aremore similar to real ambiguous words, better correspond to the actual results.Two techniques assessing the similarity are studied - the first one takesadvantage of manually created dictionaries (wordnets), the second one builds onthe automatically computed statistical data obtained from large corpora. Prosand cons of the two techniques are discussed and the results on a  standard taskare demonstrated.

Klíčová slova

pseudo-words, word sense disambiguation, evaluation, SVM

Autoři

OTRUSINA, L.; SMRŽ, P.

Rok RIV

2010

Vydáno

6. 4. 2010

Nakladatel

European Language Resources Association

Místo

Valletta

ISBN

2-9517408-6-7

Kniha

Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)

Strany od

1

Strany do

5

Strany počet

5

BibTex

@inproceedings{BUT35423,
  author="Lubomír {Otrusina} and Pavel {Smrž}",
  title="A New Approach to Pseudoword Generation",
  booktitle="Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)",
  year="2010",
  pages="1--5",
  publisher="European Language Resources Association",
  address="Valletta",
  isbn="2-9517408-6-7"
}