@article{article_505501, title={Identification of OOV words in Turkish texts}, journal={Gaziosmanpaşa Bilimsel Araştırma Dergisi}, volume={8}, pages={35–48}, year={2019}, author={Arslan, Enis and Orhan, Umut}, keywords={Bilinmeyen kelimeler,Eşdizimlilik,Birliktelik,Sözlük dışı kelimeler}, abstract={<p> <span style="font-size:10pt;font-family:’Times New Roman’, serif;">In this study, we present a semantic graph network
model which is capable of detecting out-of-vocabulary (OOV) words in Turkish
texts. In natural language processing (NLP) field, morphological analyzers can
encounter unknown words (UW) during word processing. This mostly occurs when
these kind of tools depend on a dictionary to find the probable lemmas in order
to </span> <span lang="en-us" style="font-size:10pt;font-family:’Times New Roman’, serif;" xml:lang="en-us">further process </span> <span style="font-size:10pt;font-family:’Times New Roman’, serif;"> parsing.
Sometimes, an analyzer is unable to find any candidates because of the
non-existence of the lemma candidates in the dictionary. This results in
degraded parsing output. The proposed model for OOV detection is able to define
OOV words which are suitable for dictionaries. Also co-occurrence relations of
the lemmas in texts are modelled as a semantic sub-graph and it is used to
discover collocations to propose as new lemma candidates.   </span> <br /> </p>}, number={2}, publisher={Tokat Gaziosmanpaşa Üniversitesi}