You are here

Publications

Submitted by ergin altintas on Tue, 2018-01-23 02:13

Presentations

Publications

  • 2023, Altintas, E., Development of named entity recognition system exploiting language specific features, PhD Thesis. CoHE Thesis Center (In this study, I tried to address the limitations of existing natural language processing models like BERT, which tokenize text independently of language-specific features. I introduced a language-specific approach for Turkish in natural language processing. A new tokenizer, tailored to Turkish sound transformation features, was developed, and language models trained from scratch demonstrated notable improvements in training speed and named entity recognition performance compared to existing models like BERT.)

  • 2005 Altintas, E., Karsligil E., Coskun, V., A New Semantic Similarity Measure Evaluated In Word Sense Disambiguation, The 15th Nordic Conference of Computational Linguistics (NODALIDA-2005), May 20-21 2005, Joensuu, Finland. Electronic Edition: https://aclanthology.org/W05-1702/ ; Source Code: https://gitlab.com/ealtintas/wordnet-similarity-elch (In this paper we presented a new method for measuring semantic similarity which is intended to be used in a process called word sense disambiguation, which involves determining the intended meaning of a word in a given context. This paper describes the development and evaluation of our semantic similarity measure. We tested our measure on word sense disambiguation tasks, and compare its performance to that of other existing measures. Overall, we have shown that our meause can be used to improve the accuracy of word sense disambiguation systems.)

  • 2005 Altintas, E., Karsligil E., Coskun, V., The Effect of Windowing in Word Sense Disambiguation, The 20 th International Symposium on Computer and Information Sciences (ISCIS'05), 26-28 Oct 2005, Istanbul, Turkey. Electronic Edition: https://doi.org/10.1007/11569596_65 (In this paper we investigated the impact of using different window sizes on the performance of word sense disambiguation (WSD) systems. We conducted experiments using several different window sizes (i.e., the number of surrounding words included in the context) and evaluated the impact on the performance of WSD systems. We found that using larger window sizes generally resulted in improved performance bu with a good weighting function.)

  • Improving Word Sense Disambiguation Accuracy (Master Thesis) (In my Master's thesis, I endeavored to contribute to the ongoing efforts to enhance the overall accuracy of word sense disambiguation. Building upon the foundational studies presented in the two referenced papers from 2005, I sought to advance the understanding and improvements in this field.)