EntiTables

Abstract

Tables are among the most powerful and practical tools for organizing and working with data. Our motivation is to equip spreadsheet programs with smart assistance capabilities. We concentrate on one particular family of tables, namely, tables with an entity focus. We introduce and focus on two speci c tasks: populating rows with additional instances (entities) and populating columns with new headings. We develop generative probabilistic models for both tasks. For estimating the components of these models, we consider a knowledge base as well as a large table corpus. Our experimental evaluation simulates the various stages of the user entering content into an actual table. A detailed analysis of the results shows that the models' components are complimentary and that our methods outperform existing approaches from the literature. CCS CONCEPTS•Information systems →Environment-speci c retrieval; Users and interactive retrieval; Recommender systems; Probabilistic retrieval models;

Dataset search: a survey

“…Information that is interlinked in this way allows for entity-centric searching, by identifying entities in the query and where they have similar matches in the data [150,152].…”

“…where some values are missing, fill in the missing values. This often referred to as table completion in the literature [150]. This task is like finding tables which can be unioned.…”

“…Table Completion also relies heavily on table similarity as the mechanism for finding potential values that can be added to a table. [150] defines the notion of row population, which adds additional rows to a table. For simplicity, we view this as a type of table completion in which the values to be complete form an additional row.…”

“…The task of table completion can be seen as entity set completion where the goal is to complete a list given a set of seed entities [40,150]. This task is relevant for a number of other tasks beyond table completion, including entity search [18] and knowledge base completion [39].…”

Automatic Table Union Search with Tabular Representation Learning

“…The basic idea is to map the column to a latent vector space (e.g. column representations (Bogatu et al, 2020;Chepurko et al, 2020) or token embeddings (Zhang and Balog, 2017;Herzig et al, 2020;Yang et al, 2022)) and then compute the table unionability score based on the column relation obtained from the similarity scores of col-…”