Fatma Ozcan

Fatma Ozcan

Auto-generated profile, based on publicly available information

Fatma Ozcan

Google, Sunnyvale, California, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 May 2020
Verified
Conference Paper
Open access
AQAbdul Quamar
Abdul Quamar
CLChuan Lei
Chuan Lei
DMDorian Miller
Dorian Miller
FOFatma Ozcan
Fatma Ozcan
JKJeffrey Kreulen
Jeffrey Kreulen
VEVasilis Efthymiou
Vasilis Efthymiou
Domain-specific knowledge bases (KB), carefully curated from various data sources, provide an invaluable reference for professionals. Conversation systems make these KBs easily accessible to professionals and are gaining popularity due to recent advances in natural language understanding and AI. Despite the increasing use of various conversation systems in open-domain applications, the requirements of a domain-specific conversation system are quite different and challenging. In this paper, we propose an ontology-based conversation system for domain-specific KBs. In particular, we exploit the domain knowledge inherent in the domain ontology to identify user intents, and the corresponding entities to bootstrap the conversation space. We incorporate the feedback from domain experts to further refine these patterns, and use them to generate training samples for the conversation model, lifting the heavy burden from the conversation designers. We have incorporated our innovations into a conversation agent focused on healthcare as a feature of the IBM Micromedex product.

Verified
Dataset
Closed access
NKNick R. Katsipoulakis
Nick R. Katsipoulakis
YTYuanyuan Tian
Yuanyuan Tian
FOFatma Ozcan
Fatma Ozcan
HPHamid Pirahesh
Hamid Pirahesh
BRBerthold Reinwald
Berthold Reinwald

18 May 2026 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
DLDuo Lu
Duo Lu
HCHelena Caminal
Helena Caminal
MCManos Chatzakis
Manos Chatzakis
YPYannis Papakonstantinou
Yannis Papakonstantinou
YCYannis Chronis
Yannis Chronis
FÖFatma Özcan
Fatma Özcan
Filtered Vector Search (FVS) is critical for supporting semantic search and GenAI applications in modern database systems. However, existing research most often evaluates algorithms in specialized libraries, making optimistic assumptions that do not align with enterprise-grade database systems. Our work challenges this premise by demonstrating that in a production-grade database system, commonly made assumptions do not hold, leading to performance characteristics and algorithmic trade-offs that are fundamentally different from those observed in isolated library settings. This paper presents the first in-depth analysis of filter-agnostic FVS algorithms within a production PostgreSQL-compatible system. We systematically evaluate post-filtering and inline-filtering strategies across a wide range of selectivities and correlations. Our central finding is that the optimal algorithm is not dictated by the cost of distance computations alone, but that system-level overheads that come from both distance computations and filter operations (like page accesses and data retrieval) play a significant role. We demonstrate that graph-based approaches (such as NaviX/ACORN) can incur prohibitive numbers of filter checks and system-level overheads, compared with clustering-based indexes such as ScaNN, often canceling out their theoretical benefits in real-world database environments. Ultimately, our findings provide the database community with crucial insights and practical guidelines, demonstrating that the optimal choice for a filter-agnostic FVS algorithm is not absolute, but rather a system-aware decision contingent on the interplay between workload characteristics and the underlying costs of data access in a real-world database architecture.

18 May 2026 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
YCYeounoh Chung
Yeounoh Chung
RDRushabh Desai
Rushabh Desai
JHJian He
Jian He
YXYu Xiao
Yu Xiao
THThibaud Hottelier
Thibaud Hottelier
YPYannis Papakonstantinou
Yannis Papakonstantinou
Several data warehouse and database providers have recently introduced extensions to SQL called AI Queries, enabling users to specify functions and conditions in SQL that are evaluated by LLMs, thereby broadening significantly the kinds of queries one can express over the combination of structured and unstructured data. LLMs offer remarkable semantic reasoning capabilities, making them an essential tool for complex and nuanced queries that blend structured and unstructured data. While extremely powerful, these AI queries can become prohibitively costly when invoked thousands of times. This paper provides an extensive evaluation of a recent AI query approximation approach that enables low cost analytics and database applications to benefit from AI queries. The approach delivers >100x cost and latency reduction for the semantic filter (AI.IF) operator and also important gains for semantic ranking (AI.RANK). The cost and performance gains come from utilizing cheap and accurate proxy models over embedding vectors. We show that despite the massive gains in latency and cost, these proxy models preserve accuracy and occasionally improve accuracy across various benchmark datasets, including the extended Amazon reviews benchmark that has 10M rows. We present an OLAP-friendly architecture within Google BigQuery for this approach for purely online (ad hoc) queries, and a low-latency HTAP database-friendly architecture in AlloyDB that could further improve the latency by moving the proxy model training offline. We present techniques that accelerate the proxy model training.

3 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
CLChuan Lei
Chuan Lei
RARana Alotaibi
Rana Alotaibi
AQAbdul Quamar
Abdul Quamar
VEVasilis Efthymiou
Vasilis Efthymiou
FÖFatma Özcan
Fatma Özcan
Enterprises are creating domain-specific knowledge graphs by curating and integrating their business data from multiple sources. The data in these knowledge graphs can be described using ontologies, which provide a semantic abstraction to define the content in terms of the entities and the relationships of the domain. The rich semantic relationships in an ontology contain a variety of opportunities to reduce edge traversals and consequently improve the graph query performance. Although there has been a lot of effort to build systems that enable efficient querying over knowledge graphs, the problem of schema optimization for query performance has been largely ignored in the graph setting. In this work, we show that graph schema design has significant impact on query performance, and then propose optimization algorithms that exploit the opportunities from the domain ontology to generate efficient property graph schemas. To the best of our knowledge, we are the first to present an ontology-driven approach for property graph schema optimization. We conduct empirical evaluations with two real-world knowledge graphs from medical and financial domains. The results show that the schemas produced by the optimization algorithms achieve up to 2 orders of magnitude speed-up compared to the baseline approach.

2 April 2026 in Proceedings of the ACM on Management of Data
Verified
Journal Article
Open access
GKGaurav Tarlok Kakkar
Gaurav Tarlok Kakkar
YCYeounoh Chung
Yeounoh Chung
FÖFatma Özcan
Fatma Özcan
SMSteve Mussmann
Steve Mussmann
JAJoy Arulraj
Joy Arulraj
Large language models (LLMs) have achieved strong performance on natural language to SQL (NL2SQL) tasks, but their practical effectiveness depends on tuning a complex pipeline of interacting components. Real-world deployments must navigate a critical trade-off between execution accuracy and monetary cost, a factor that has been largely overlooked by prior work focused primarily on maximizing accuracy. Navigating this trade-off is non-trivial: the ideal configuration of components (e.g., LLM, prompting strategy, schema linking) is not only interdependent but also highly sensitive to the target database schema. This creates a challenging, schema-aware configuration tuning problem that lacks a systematic solution. We present PRISM, a framework that systematically identifies high-accuracy, cost-efficient NL2SQL configurations tailored to each schema. Adopting an optimize-then-deploy strategy, PRISM first uses cost-aware Bayesian Optimization in an offline phase to efficiently explore the configuration space and curate a pool of high-performing pipelines. In an online phase, it deploys these configurations either as a single, cost-effective candidate or as an ensemble to maximize accuracy. Experiments on the BIRD benchmark demonstrate that PRISM achieves 69.48% execution accuracy in the single-candidate setting, improving accuracy by 2.34% over the strongest baseline while reducing cost by 92%. In the ensemble setting, PRISM boosts accuracy further to 74.9%.