Year: 2018
Type: conference-paper
Abstract: Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG.This problem can be challenging when the form of the structured data varies between examples.This paper presents a survey of several extensions to sequence-to-sequence models to account for the latent content selection process, particularly variants of copy attention and coverage decoding.We further propose a training method based on diverse ensembling to encourage models to learn distinct sentence templates during training.An empirical evaluation of these techniques shows an increase in the quality of generated text across five automated metrics, as well as human evaluation.
DOI: 10.18653/v1/w18-6505
Institutions: Harvard University, Toyota Technological Institute at Chicago
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: Samsung
OpenAlex ID: W2897164851
