Filtreler

2020 - 20252
Filtreleri Sıfırla

Ayarlar

Yazar: Gümüşçekiçci, Gizem × Bölüm: Işık University, Faculty of Engineering, Department of Computer Engineering ×

Arama Sonuçları

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Yayın
    Web service translating content into Turkish sign language
    (Institute of Electrical and Electronics Engineers Inc., 2020-10-12) Gümüşçekiçci, Gizem; Ezerceli, Özay; Tek, Faik Boray
    The essential communication tool for people with hearing loss is sign language. It is way more efficient for their communication. Existing systems for translating the text into sign language are offline and not practical. In this study, we propose a web service-based solution for online translation of content into Turkish Sign Language. We implemented the system and tested it using 32 sentences of 189 words as inputs. The correct word translation rate was 81.74% for the media or audio inputs and the correct word translation for the text inputs was 81.09% The results show the feasibility of the solution and the potential for improvements.
  • Küçük Resim
    Yayın
    Sarcasm detection on news headlines using transformers
    (Springer, 2025-09-07) Gümüşçekiçci, Gizem; Dehkharghani, Rahim
    Sarcasm poses a linguistic challenge due to its figurative nature, where intended meaning contradicts literal interpretation. Sarcasm is prevalent in human communication, affecting interactions in literature, social media, news, e-commerce, etc. Identifying the true intent behind sarcasm is challenging but essential for applications in sentiment analysis. Detecting sarcasm in written text, as a challenging task, has attracted many researchers in recent years. This paper attempts to detect sarcasm in news headlines. Journalists prefer using sarcastic news headlines as they seem much more interesting to the readers. In the proposed methodology, we experimented with Transformers, namely the BERT model, and several Machine and Deep Learning models with different word and sentence embedding methods. The proposed approach inherently requires high-performance resources due to the use of large-scale pre-trained language models such as BERT. We also extended an existing news headlines dataset for sarcasm detection using augmentation techniques and annotating it with hand-crafted features. The proposed methodology could outperform almost all existing sarcasm detection approaches with a 98.86% F1-score when applied to the extended news headlines dataset, which we made publicly available on GitHub.