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

It is common for people to create different types of charts to explore a multi-dimensional dataset (table). However, to build a real-world intelligent assistant that recommends commonly composed charts, it should take the challenges of efficiency, imbalanced data hungry and table context into consideration. 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 167k tables and 271k 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 outperforms other chart recommendation systems in both multi-type task (with almost doubled recall numbers R@3=0.62 and R@1=0.44) and human evaluations.