Unsupervised Text Generation from Structured Data

04/20/2019
by   Martin Schmitt, et al.
0

This work presents a joint solution to two challenging tasks: text generation from data and open information extraction. We propose to model both tasks as sequence-to-sequence translation problems and thus construct a joint neural model for both. Our experiments on knowledge graphs from Visual Genome, i.e., structured image analyses, shows promising results compared to strong baselines. Building on recent work on unsupervised machine translation, we report the first results - to the best of our knowledge - on fully unsupervised text generation from structured data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/18/2020

Unsupervised Pidgin Text Generation By Pivoting English Data and Self-Training

West African Pidgin English is a language that is significantly spoken i...
research
05/05/2020

Smart To-Do : Automatic Generation of To-Do Items from Emails

Intelligent features in email service applications aim to increase produ...
research
10/23/2018

Deep Graph Convolutional Encoders for Structured Data to Text Generation

Most previous work on neural text generation from graph-structured data ...
research
10/02/2019

Clinical Text Generation through Leveraging Medical Concept and Relations

With a neural sequence generation model, this study aims to develop a me...
research
06/08/2020

CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training

Two important tasks at the intersection of knowledge graphs and natural ...
research
09/22/2022

INFINITY: A Simple Yet Effective Unsupervised Framework for Graph-Text Mutual Conversion

Graph-to-text (G2T) generation and text-to-graph (T2G) triple extraction...
research
06/29/2023

Joint Level Generation and Translation Using Gameplay Videos

Procedural Content Generation via Machine Learning (PCGML) faces a signi...

Please sign up or login with your details

Forgot password? Click here to reset