Sequence-to-Sequence Models for Data-to-Text Natural Language Generation: Word- vs. Character-based Processing and Output Diversity

10/11/2018
by   Glorianna Jagfeld, et al.
0

We present a comparison of word-based and character-based sequence-to-sequence models for data-to-text natural language generation, which generate natural language descriptions for structured inputs. On the datasets of two recent generation challenges, our models achieve comparable or better automatic evaluation results than the best challenge submissions. Subsequent detailed statistical and human analyses shed light on the differences between the two input representations and the diversity of the generated texts. In a controlled experiment with synthetic training data generated from templates, we demonstrate the ability of neural models to learn novel combinations of the templates and thereby generalize beyond the linguistic structures they were trained on.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/10/2018

End-to-End Content and Plan Selection for Data-to-Text Generation

Learning to generate fluent natural language from structured data with n...
research
09/19/2018

String Transduction with Target Language Models and Insertion Handling

Many character-level tasks can be framed as sequence-to-sequence transdu...
research
06/16/2021

Automatic Construction of Evaluation Suites for Natural Language Generation Datasets

Machine learning approaches applied to NLP are often evaluated by summar...
research
11/08/2020

Best Practices for Data-Efficient Modeling in NLG:How to Train Production-Ready Neural Models with Less Data

Natural language generation (NLG) is a critical component in conversatio...
research
01/23/2019

Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge

This paper provides a detailed summary of the first shared task on End-t...
research
04/26/2019

Copy mechanism and tailored training for character-based data-to-text generation

In the last few years, many different methods have been focusing on usin...
research
08/18/2017

Assessing the Stylistic Properties of Neurally Generated Text in Authorship Attribution

Recent applications of neural language models have led to an increased i...

Please sign up or login with your details

Forgot password? Click here to reset