Related papers: Columnar Formats for Schemaless LSM-based Document…
We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentences into blocks of increasing complexity. Our Structure…
The rapid increase in textual information means we need more efficient methods to sift through, organize, and understand it all. While retrieval-augmented generation (RAG) models excel in accessing information from large document…
Index structures are important for efficient data access, which have been widely used to improve the performance in many in-memory systems. Due to high in-memory overheads, traditional index structures become difficult to process the…
Semi-structured documents integrate diverse interleaved data elements (e.g., tables, charts, hierarchical paragraphs) arranged in various and often irregular layouts. These documents are widely observed across domains and account for a…
Parallel shared-nothing data management systems have been widely used to exploit a cluster of machines for efficient and scalable data processing. When a cluster needs to be dynamically scaled in or out, data must be efficiently rebalanced.…
Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of structured variables. This challenge is particularly acute in domains like clinical medicine,…
In this paper, we present the guidelines for an XML-based approach for the sociological study of Web data such as the analysis of mailing lists or databases available online. The use of an XML warehouse is a flexible solution for storing…
By introducing intermediate states for metadata changes and ensuring that at most two versions of metadata exist in the cluster at the same time, shared-nothing databases are capable of making online, asynchronous schema changes. However,…
We propose a novel framework for summarizing structured enterprise data across multiple dimensions using large language model (LLM)-based agents. Traditional table-to-text models often lack the capacity to reason across hierarchical…
The integration of heterogeneous databases into a unified querying framework remains a critical challenge, particularly in resource-constrained environments. This paper presents a novel Small Language Model(SLM)-driven system that…
Data lakes have emerged as an alternative to data warehouses for the storage, exploration and analysis of big data. In a data lake, data are stored in a raw state and bear no explicit schema. Thence, an efficient metadata system is…
Large language models (LLMs) are advancing rapidly. Such models have demonstrated strong capabilities in learning from large-scale (unstructured) text data and answering user queries. Users do not need to be experts in structured query…
Most recently, researchers have started building large language models (LLMs) powered data systems that allow users to analyze unstructured text documents like working with a database because LLMs are very effective in extracting attributes…
Recursive queries and recursive derived tables constitute an important part of the SQL standard. Their efficient processing is important for many real-life applications that rely on graph or hierarchy traversal. Position-enabled…
We present a study on the integration of Large Language Models (LLMs) in tabular data classification, emphasizing an efficient framework. Building upon existing work done in TabLLM (arXiv:2210.10723), we introduce three novel serialization…
Document parsing (DP) transforms unstructured or semi-structured documents into structured, machine-readable representations, enabling downstream applications such as knowledge base construction and retrieval-augmented generation (RAG).…
The multi-level design of Log-Structured Merge-trees (LSM-trees) naturally fits the tiered storage architecture: the upper levels (recently inserted/updated records) are kept in fast storage to guarantee performance while the lower levels…
The Log Structured Merge Trees (LSM-tree) based key-value stores are widely used in many storage systems to support a variety of operations such as updates, point reads, and range reads. Traditionally, LSM-tree's merge policy organizes data…
Medical multi-document summarization (MDS) is a complex task that requires effectively managing cross-document relationships. This paper investigates whether incorporating hierarchical structures in the inputs of MDS can improve a model's…
In this work, we study the cost efficient data versioning problem, where the goal is to optimize the storage and reconstruction (retrieval) costs of data versions, given a graph of datasets as nodes and edges capturing edit/delta…