Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1809762, author = {Kovář, Vojtěch and Rychlý, Pavel}, address = {Brno}, booktitle = {Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)}, editor = {Horák, Aleš; Rychlý, Pavel; Rambousek, Adam}, keywords = {Lemmatization; Morphological guesser; Morphological analysis; Morphological guessing}, howpublished = {tištěná verze "print"}, language = {eng}, location = {Brno}, isbn = {978-80-263-1670-1}, pages = {135-138}, publisher = {Tribun EU}, title = {DMoG : A Data-Based Morphological Guesser}, url = {https://nlp.fi.muni.cz/raslan/raslan21.pdf#page=143}, year = {2021} }
TY - JOUR ID - 1809762 AU - Kovář, Vojtěch - Rychlý, Pavel PY - 2021 TI - DMoG : A Data-Based Morphological Guesser PB - Tribun EU CY - Brno SN - 9788026316701 KW - Lemmatization KW - Morphological guesser KW - Morphological analysis KW - Morphological guessing UR - https://nlp.fi.muni.cz/raslan/raslan21.pdf#page=143 N2 - We present a novel corpus-based approach to lemmatization of unknown words. The tool learns affix patterns from annotated data, and based on these patterns, it predicts other word forms that should be present in the corpus. A lemma candidate then comes from the pattern whose predictions are really found in the corpus. We present a prototype implementation and an initial evaluation on Czech, which shows promising results. ER -
KOVÁŘ, Vojtěch and Pavel RYCHLÝ. DMoG : A Data-Based Morphological Guesser. In Horák, Aleš; Rychlý, Pavel; Rambousek, Adam. \textit{Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)}. Brno: Tribun EU, 2021, p.~135-138. ISBN~978-80-263-1670-1.
|