TR-Dizin İndeksli Yayınlar Koleksiyonu / TR Dizin Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1927

Browse

Now showing 1 - 5 of 5

Mention Detection in Turkish Coreference Resolution
(Tubitak Scientific & Technological Research Council Turkey, 2024) Demir, Seniz; Akdag, Hanifi Ibrahim
A crucial step in understanding natural language is detecting mentions that refer to real-world entities in a text and correctly identifying their boundaries. Mention detection is commonly considered a preprocessing step in coreference resolution which is shown to be helpful in several language processing applications such as machine translation and text summarization. Despite recent efforts on Turkish coreference resolution, no standalone neural solution to mention detection has been proposed yet. In this article, we present two models designed for detecting Turkish mentions by using feed-forward neural networks. Both models extract all spans up to a fixed length from input text as candidates and classify them as mentions or not mentions. The models differ in terms of how candidate text spans are represented. The first model represents a span by focusing on its first and last words, whereas the representation also covers the preceding and proceeding words of a span in the second model. Mention span representations are formed by using contextual embeddings, part-of-speech embeddings, and named-entity embeddings of words in interest where contextual embeddings are obtained from pretrained Turkish language models. In our evaluation studies, we not only assess the impact of mention representation strategies on system performance but also demonstrate the usability of different pretrained language models in resolution task. We argue that our work provides useful insights to the existing literature and the first step in understanding the effectiveness of neural architectures in Turkish mention detection.
Citation - WoS: 1
Citation - Scopus: 1
Us Policies Adrift in a Levant in Turmoil
(Stradigma, 2018) Özel, Soli; Görmüş, Evrim
The Levant has constituted one of the core areas of interest for US foreign policy since the Second World War. The aim of this article is to shed light on the US policies towards the Levant, mostly during the last two American administrations, to understand how the vicissitudes of the region and of American politics made Washington’s policy towards the Levant look biased, at times incompetent, and most importantly inconsistent. This article examines the changes in approach to the region as a whole from one administration to the next on issues such as the protection of Israel’s sovereignty, supporting friendly regimes, fighting terrorism, and containing Iran. The hesitations and shifts in policy towards Syria are given a longer treatment as they speak both to the yet not finalized American policy towards the Levant but also to show how the US has shifted track and moved away from unseating President Assad to focus more on containing and if possible rolling over Iran.
Citation - WoS: 1
Citation - Scopus: 1
Determining and Evaluating New Store Locations Using Remote Sensing and Machine Learning
(Tübitak, 2021) Ünsalan, Cem; Turgay, Zeynep Zerrin; Küçükaydın, Hande; Höke, Berkan
Decision making for store locations is crucial for retail companies as the profit depends on the location. The key point for correct store location is profit approximation, which is highly dependent on population of the corresponding region, and hence, the volume of the residential area. Thus, estimating building volumes provides insight about the revenue if a new store is about to be opened there. Remote sensing through stereo/tri-stereo satellite images provides wide area coverage as well as adequate resolution for three dimensional reconstruction for volume estimation. We reconstruct 3D map of corresponding region with the help of semiglobal matching and mask R-CNN algorithms for this purpose. Using the existing store data, we construct models for estimating the revenue based on surrounding building volumes. In order to choose the right location, the suitable utility model, which calculates store revenues, shouldbe rigorously determined. Moreover, model parameters should be assessed as correctly as possible. Instead of using randomly generated parameters, we employ remote sensing, computer vision, and machine learning techniques, which provide a novel way for evaluating new store locations.
Citation - WoS: 4
Citation - Scopus: 6
Turkey's Green Imagination: the Spatiality of the Low-Carbon Energy Transition Within the Eu Green Deal
(Uluslararasi Iliskiler Konseyi Dernegi, 2023) Akçalı, Emel; Özel, Soli; Görmüş, Evrim
This article asks the extent to which the EU Green Deal influences the EU periphery today and builds on the spatial conditions of multiple, co-existing decarbonization pathways within the EU Green Deal while problematizing the 'green imagination' of Turkey as an immediate neighbour and a candidate country for membership in the EU. As such, it uncovers that the current low-carbon transition process in Turkey is prone to be shaped by the highly politicized energy market in an authoritarian neoliberal structure on the one hand, and Turkey's priorities in energy issues and hard security on the other. The findings further reveal that Turkey's efforts to use more domestic energy resources to meet its consumption needs might also interfere with its efforts and obligations to decarbonize its energy sector. The scrutiny into the low-carbon energy transition in Turkey accordingl contributes further insight into the consequences of the spatiality of such transitions in an authoritarian neoliberal context, and what other alternative policies can be imagined and put in practice. Thus, more empirical research is warranted to reveal the spatiality of the low-carbon energy transition across various geographical settings. At the same time, the article argues that both the EU and its partners such as Turkey should be weary of creating green utopias when redesigning their green-energy space since utopias tout court may not always stimulate large-scale change in a revolutionary way in terms of sustainability, feasibility, good practice, and inclusiveness in decision-making processes.
Citation - WoS: 3
Citation - Scopus: 5
Consumer Loans' First Payment Default Detection: a Predictive Model
(TUBITAK SCIENTIFIC & TECHNICAL RESEARCH COUNCIL, 2020) Sevgili, Türkan; Koç, Utku
A default loan (also called nonperforming loan) occurs when there is a failure to meet bank conditions and repayment cannot be made in accordance with the terms of the loan which has reached its maturity. In this study, we provide a predictive analysis of the consumer behavior concerning a loan’s first payment default (FPD) using a real dataset of consumer loans with approximately 600,000 records from a bank. We use logistic regression, naive Bayes, support vector machine, and random forest on oversampled and undersampled data to build eight different models to predict FPD loans. A two-class random forest using undersampling yielded more than 86% on all performance measures: accuracy, precision, recall, and F1-score. The corresponding scores are even as high as 96% for oversampling. However, when tested on the real and balanced dataset, the performance of oversampling deteriorates as generating synthetic data for an extremely imbalanced dataset harms the training procedure of the algorithms. The study also provides an understanding of the reasons for nonperforming loans and helps to manage credit risks more consciously.

Browse

Browsing TR-Dizin İndeksli Yayınlar Koleksiyonu / TR Dizin Indexed Publications Collection by Scopus Q "Q2"