SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.06749 · ACL · 2020

Structural Information Preserving for Graph-to-Text Generation

Kun Xu, Yue Zhang, Dong Yu, Linfeng Song, Jinsong Su, Yubin Ge, Ante Wang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The task of graph-to-text generation aims at producing sentences that preserve the meaning of input graphs. As a crucial defect, the current state-of-the-art models may mess up or even drop the core structural information of input graphs when generating outputs. We propose to tackle this problem by leveraging richer training signals that can guide our model for preserving input information. In particular, we introduce two types of autoencoding losses, each individually focusing on different aspects (a.k.a. views) of input graphs. The losses are then back-propagated to better calibrate our model via multi-task training. Experiments on two benchmarks for graph-to-text generation show the effectiveness of our approach over a state-of-the-art baseline. Our code is available at http://github.com/ Soistesimmer/AMR-multiview.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2102.06749")
get_code_for_paper("2102.06749")
have("2102.06749")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2102.06749.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2102.06749.svg)](https://syntology.ai/paper/2102.06749)

Connect an agent — have() is free.