Dilan Bakir

dblp:325/2837 · DBLP profile ↗
← Back
2ranked-venue papers in the field
2as first author
2since 2021 · last 2023
0000-0001-6650-6942ORCID · reported

Domains — venue-derived; a paper can count in several

Big Data, Cloud & Distributed Data Systems · 2 (2 first)
YearPublicationVenuePosition
2023 Developing and Evaluating a Model-Based Metric for Legal Question Answering Systems
abstract
In the complicated world of legal law, Question Answering (QA) systems only work if they can give correct, situation-aware, and logically sound answers. Traditional evaluation methods, which rely on superficial similarity measures, can’t catch the complex accuracy and reasoning needed in legal answers. This means that evaluation methods need to change completely. To fix the problems with current methods, this study presents a new model-based evaluation metric that is designed to work well with legal QA systems. We are looking into the basic ideas that are needed for this kind of metric, as well as the problems of putting it into practice in the real world, finding the right technological frameworks, creating good evaluation methods. We talk about a theory framework that is based on legal standards and computational linguistics. We also talk about how the metric was created and how it can be used in real life. Our results, which come from thorough tests, show that our suggested measure is better than existing ones. It is more reliable, accurate, and useful for judging legal quality assurance systems.
Dilan Bakir, Beytullah Yildiz, Mehmet S. Aktas
IEEE Big Data1
2022 A Business Workflow For Providing Open-Domain Question Answering Reader Systems on The Wikipedia Dataset
abstract
In a variety of sectors, we observe the emerging need for responding to user questions in a fast and efficient manner. We argue that addressing this need by developing question answering reader system applications will lead to several benefits: a) the density of call centers is reduced, and b) time is saved by getting answers through the application instead of going to the company itself. Examples of these applications, such as search engines help users find answers to their questions on documents containing important information, such as legal documents. These applications can be applied in digital banking, electronic commerce, and legal documents. In this study, we investigate the design of a business workflow that can provide answers to questions through documents containing important information, such as legal documents. In this study, we examine open-domain reader systems and propose a business workflow for open-domain reader systems. We are implementing a prototype application on the dataset to investigate the usability of the proposed business workflow. We discuss the prototype’s implementation details and share its evaluation results. The results show that the T5-based model provides better results in open-domain reader systems.
Dilan Bakir, Mehmet S. Aktas
IEEE Big Data1