DeepAI AI Chat
Log In Sign Up

Table2Charts: Learning Shared Representations for Recommending Charts on Multi-dimensional Data

by   Mengyu Zhou, et al.

It is common for people to create different types of charts to explore a multi-dimensional dataset (table). However, to build an intelligent assistant that recommends commonly composed charts, the fundamental problems of "multi-dialect" unification, imbalanced data and open vocabulary exist. In this paper, we propose Table2Charts framework which learns common patterns from a large corpus of (table, charts) pairs. Based on deep Q-learning with copying mechanism and heuristic searching, Table2Charts does table-to-sequence generation, where each sequence follows a chart template. On a large spreadsheet corpus with 196k tables and 306k charts, we show that Table2Charts could learn a shared representation of table fields so that tasks on different chart types could mutually enhance each other. Table2Charts has >0.61 recall at top-3 and >0.49 recall at top-1 for both single-type and multi-type chart recommendation tasks.


page 14

page 17

page 20


Typed Table Transformations

Spreadsheet tables are often labeled, and these labels effectively const...

GitTables: A Large-Scale Corpus of Relational Tables

The practical success of deep learning has sparked interest in improving...

Optimized Table Tokenization for Table Structure Recognition

Extracting tables from documents is a crucial task in any document conve...

Implementation Strategies for Multidimensional Spreadsheets

Seasoned Excel developers were invited to participate in a challenge to ...

nBIIG: A Neural BI Insights Generation System for Table Reporting

We present nBIIG, a neural Business Intelligence (BI) Insights Generatio...

An Efficient Machine-Learning Approach for PDF Tabulation in Turbulent Combustion Closure

Probability density function (PDF) based turbulent combustion modelling ...