Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning

05/08/2022
by   Fei Wang, et al.
0

Controlled table-to-text generation seeks to generate natural language descriptions for highlighted subparts of a table. Previous SOTA systems still employ a sequence-to-sequence generation method, which merely captures the table as a linear structure and is brittle when table layouts change. We seek to go beyond this paradigm by (1) effectively expressing the relations of content pieces in the table, and (2) making our model robust to content-invariant structural transformations. Accordingly, we propose an equivariance learning framework, which encodes tables with a structure-aware self-attention mechanism. This prunes the full self-attention structure into an order-invariant graph attention that captures the connected graph structure of cells belonging to the same row or column, and it differentiates between relevant cells and irrelevant cells from the structural perspective. Our framework also modifies the positional encoding mechanism to preserve the relative position of tokens in the same cell but enforce position invariance among different cells. Our technology is free to be plugged into existing table-to-text generation models, and has improved T5-based models to offer better performance on ToTTo and HiTab. Moreover, on a harder version of ToTTo, we preserve promising performance, while previous SOTA systems, even with transformation-based data augmentation, have seen significant performance drops. Our code is available at https://github.com/luka-group/Lattice.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/27/2017

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

Table-to-text generation aims to generate a description for a factual ta...
research
01/05/2023

Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach

Although remarkable progress on the neural table-to-text methods has bee...
research
05/04/2021

Retrieving Complex Tables with Multi-Granular Graph Representation Learning

The task of natural language table retrieval (NLTR) seeks to retrieve se...
research
02/06/2023

LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control

Logical Table-to-Text (LT2T) generation is tasked with generating logica...
research
05/31/2023

A Sequence-to-Sequence Set Model for Text-to-Table Generation

Recently, the text-to-table generation task has attracted increasing att...
research
02/20/2023

Improving User Controlled Table-To-Text Generation Robustness

In this work we study user controlled table-to-text generation where use...
research
01/01/2019

Text Infilling

Recent years have seen remarkable progress of text generation in differe...

Please sign up or login with your details

Forgot password? Click here to reset