The integration of tabular data from diverse sources is often hindered by inconsistencies in formatting and representation, posing significant challenges for data analysts and personal digital assistants. Existing methods for automating tabular data transformations are limited in scope, often focusing on specific types of transformations or lacking interpretability. In this paper, we introduce TabulaX, a novel framework that leverages Large Language Models (LLMs) for multi-class column-level tabular transformations. TabulaX first classifies input columns into four transformation types—string-based, numerical, algorithmic, and general—and then applies tailored methods to generate human-interpretable transformation functions, such as numeric formulas or programming code. This approach enhances transparency and allows users to understand and modify the mappings. Through extensive experiments on real-world datasets from various domains, we demonstrate that TabulaX outperforms existing state-of-the-art approaches in terms of accuracy, supports a broader class of transformations, and generates interpretable transformations that can be efficiently applied.

Many organizations rely on data from government and third-party sources, and those sources rarely follow the same data formatting. This introduces challenges in integrating data from multiple sources or aligning external sources with internal databases. Commercial database systems do not offer adequate support for integrating data from heterogeneous sources, and manual integration is both time-consuming and inefficient. State-of-the-art data integration approaches that rely on similarity functions and textual transformations often fail to handle challenging cases where multiple mappings are required, or the mappings go beyond simple textual transformations. In this paper, we study the potentials of deep neural models for transforming tables for joinability. In particular, we cast the problem as a prediction task and develop a framework that leverages large deep-learning language models to transform tabular data from a source formatting to a desired target representation. Our framework can efficiently learn the patterns for mapping a source formatting into an expected target using just a few examples, which can then be used for tasks such as table joining, filling in missing values, and error detection. Compared to state-of-the-art mapping and joining approaches, our framework delivers noticeably more accurate and scalable performance on both real-world and synthetic datasets. Our experimental evaluation also shows that the performance of the proposed framework using our fine-tuned model is at par or better than large language models such as GPT-3, despite the significant difference in size, and that using large language models within our framework improves their performance.

Data from different sources rarely conform to a single formatting even if they describe the same set of entities, and this raises concerns when data from multiple sources must be joined or cross-referenced. Such a formatting mismatch is unavoidable when data is gathered from various public and third-party sources. Commercial database systems are not able to perform the join when there exist differences in data representation or formatting, and manual reformatting is both time consuming and error-prone. We study the problem of efficiently joining textual data under the condition that the join columns are not formatted the same and cannot be equi-joined, but they become joinable under some transformations. The problem is challenging simply because the number of possible transformations explodes with both the length of the input and the number of rows, even if each transformation is formed using very few basic units. We show that an efficient algorithm can be developed based on the common characteristics of the joined columns and over a rich set of basic operations that can be composed to form transformations. Compared to a state-of-the-art approach, our algorithm covers every transformation that is covered in the state-of-the-art approach but is a few orders of magnitude faster, as evaluated on various real and synthetic data.

Understanding searchers' queries is an essential component of semantic search systems. In many cases, search queries involve specific attributes of an entity in a knowledge base (KB), which can be further used to find query answers. In this study, we aim to move forward the understanding of queries by identifying their related entity attributes from a knowledge base. To this end, we introduce the task of entity attribute identification and propose two methods to address it: (i) a model based on Markov Random Field, and (ii) a learning to rank model. We develop a human annotated test collection and show that our proposed methods can bring significant improvements over the baseline methods.

Telegram has become one of the most successful instant messaging services in recent years. In this paper, we developed a crawler to gather its public data. To the best of our knowledge, this paper is the first attempt to analyze the structural and topical aspects of messages published in Telegram instant messaging service using crawled data. We also extracted the mention graph and page rank of our data collection which indicates important differences between linking patterns of Telegram nodes and other usual networks. We also classified messages to detect advertisement and spam messages.

Finding talented users on Stackoverflow can be a challenging task due to term mismatch between queries and content published on it. In this paper, we propose two translation models to augment a given query with relevant words. The first model is based on a statistical approach and the second one is a word embedding model. Interestingly, the translations provided by these methods are not the same. Although the first model in most cases selects pieces of program codes as translations, the second model provides more semantically related words. Our experiments on a large dataset indicate the efficiency of proposed models.