Table-to-text Generation by Structure-aware Seq2seq Learning

TL;DR

This paper introduces a novel structure-aware seq2seq model for table-to-text generation that effectively encodes table content and structure, leading to more coherent and informative descriptions, validated on Wikipedia biographies.

Contribution

The paper proposes a field-gating encoder and dual attention decoder to better incorporate table structure into text generation, outperforming existing methods.

Findings

Outperforms baseline models significantly on WIKIBIO dataset

Generates coherent descriptions with better content relevance

Visualizations demonstrate effective understanding of table structure

Abstract

Table-to-text generation aims to generate a description for a factual table which can be viewed as a set of field-value records. To encode both the content and the structure of a table, we propose a novel structure-aware seq2seq architecture which consists of field-gating encoder and description generator with dual attention. In the encoding phase, we update the cell memory of the LSTM unit by a field gate and its corresponding field value in order to incorporate field information into table representation. In the decoding phase, dual attention mechanism which contains word level attention and field level attention is proposed to model the semantic relevance between the generated description and the table. We conduct experiments on the \texttt{WIKIBIO} dataset which contains over 700k biographies and corresponding infoboxes from Wikipedia. The attention visualizations and case studies show that our model is capable of generating coherent and informative descriptions based on the comprehensive understanding of both the content and the structure of a table. Automatic evaluations also show our model outperforms the baselines by a great margin. Code for this work is available on https://github.com/tyliupku/wiki2bio.