TR Dizin İndeksli Yayınlar / TR Dizin Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7149
Browse
2 results
Search Results
Now showing 1 - 2 of 2
Article Citation - WoS: 2Citation - Scopus: 2Enrichment of Turkish Question Answering Systems Using Knowledge Graphs(Tubitak Scientific & Technological Research Council Turkey, 2024) Ciftci, Okan; Soygazi, Fatih; Tekir, SelmaRecent capabilities of large language models (LLMs) have transformed many tasks in Natural Language Processing (NLP), including question answering. The state-of-the-art systems do an excellent job of responding in a relevant, persuasive way but cannot guarantee factuality. Knowledge graphs, representing facts as triplets, can be valuable for avoiding errors and inconsistencies with real-world facts. This work introduces a knowledge graph-based approach to Turkish question answering. The proposed approach aims to develop a methodology capable of drawing inferences from a knowledge graph to answer complex multihop questions. We construct the Beyazperde Movie Knowledge Graph (BPMovieKG) and the Turkish Movie Question Answering dataset (TRMQA) to answer questions in the movie domain. We evaluate our proposed question answering pipeline against a baseline study. Furthermore, we compare it with a question answering system built upon GPT-3.5 Turbo to answer the 1-hop questions from TRMQA. The experimental results confirm that link prediction on a knowledge graph is quite effective in answering questions that require reasoning paths. Finally, we provide insights into the pros and cons of the provided solution through a qualitative study.Article Performance Analysis of K-Degree Anonymization on Barabási-Albert Graph(2023) Soygazi, Fatih; Oğuz, DamlaAnonymity is one the most important problems that emerged with the increasing number of graph-based social networks. It is not straightforward to ensure anonymity by adding or removing some nodes from the graph. Therefore, a more sophisticated approach is required. The consideration of the degree of the nodes in a graph may facilitate having knowledge about specific nodes. To handle this problem, one of the prominent solutions is k-degree anonymization where some nodes involving particular degree values are anonymized by masking its information from the attackers. Our objective is to evaluate the achievement of k-degree anonymization with a well-known graph structure, namely, Barabási-Albert graph, which is similar to the graphs on social networks. Hence, we generate multiple synthetic Barabási-Albert graphs and evaluate the k-degree anonymization performance on these graphs. According to experimental results, the success of k-degree anonymity approximately proportional to the number of edges or nodes.