Given a user query containing ambiguous and user-specific references, how can we effectively retrieve personalized information? Personalized information retrieval (PIR) requires resolving context-dependent cues --- such as nicknames, personal locations, or temporal expressions. This poses challenges for conventional retrievers, including dense and generative models, which often struggle with entity ambiguity and generalization to user-specific contexts. In this paper, we propose PEARL (Personalized Entity-Aware Generative RetrievaL), a novel generative retrieval framework for personalized IR. PEARL addresses key challenges through three components: (i) entity-aware annotation with span-level regularization to reduce lexical sensitivity, (ii) prefix-based contrastive learning to capture structural alignment between lexically divergent query-passage pairs, and (iii) context diversification to improve robustness against user-specific variations. Empirical results on both an existing PIR dataset and our new large-scale synthetic benchmark PAIR show that PEARL consistently outperforms strong baselines under zero-shot evaluation. Notably, PEARL achieves the state-of-the-art performance in Hits@1 and MRR@10, demonstrating its effectiveness for retrieval in personalized user contexts. Our dataset is available at https://www.github.com/pearl-pair/pearl.

This article proposes an index key compression scheme based on the notion of distinction bits. It proves that the distinction bits of index keys are sufficient information to determine the sorted order of the index keys. The actual compression ratio may vary depending on the characteristics of datasets (an average of 2.76:1 compression ratio was observed in the authors’ experiments). However, the index key compression scheme leads to significant performance improvements during the reconstruction of large-scale indexes. This study’s index key compression can be effectively used for database replication and index recovery in modern main-memory database systems.

Business planning as well as analytics on top of large-scale database systems is valuable to decision makers, but planning operations known and implemented so far are very basic. In this paper we propose a new planning operation called interval disaggregate , which goes as follows. Suppose that the planner, typically the management of a company, plans sales revenues of its products in the current year. An interval of the expected revenue for each product in the current year is computed from historical data in the database as the prediction interval of linear regression on the data. A total target revenue for the current year is given by the planner. The goal of the interval disaggregate operation is to find an appropriate disaggregation of the target revenue, considering the intervals. We formulate the problem of interval disaggregation more precisely and give solutions for the problem. Multidimensional geometry plays a crucial role in the problem formulation and the solutions. We implemented interval disaggregation into the planning engine of SAP HANA and did experiments on real-world data. Our experiments show that interval disaggregation gives more appropriate solutions with respect to historical data than the known basic disaggregation called referential disaggregation. We also show that interval disaggregation can be combined with the deseasonalization technique when the dataset shows seasonal fluctuations.

This paper addresses a customization process of a Korean-English MT system for patent translation. The major customization steps include terminology construction, linguistic study, and the modification of the existing analysis and generation-module. T o our knowledge, this is the first worth-mentioning large-scale customization effort of an MT system for Korean and English. This research was performed under the auspices of the MIC (Ministry of Information and Communication) of Korean government. A prototype patent MT system for electronics domain was installed and is being tested in the Korean Intellectual Property Office.