Skip to main content

Research Repository

Advanced Search

A divide-and-conquer approach to neural natural language generation from structured data

Dethlefs, Nina; Schoene, Annika; Cuayáhuitl, Heriberto

Authors

Annika Schoene

Heriberto Cuayáhuitl



Abstract

Current approaches that generate text from linked data for complex real-world domains can face problems including rich and sparse vocabularies as well as learning from examples of long varied sequences. In this article, we propose a novel divide-and-conquer approach that automatically induces a hierarchy of “generation spaces” from a dataset of semantic concepts and texts. Generation spaces are based on a notion of similarity of partial knowledge graphs that represent the domain and feed into a hierarchy of sequence-to-sequence or memory-to-sequence learners for concept-to-text generation. An advantage of our approach is that learning models are exposed to the most relevant examples during training which can avoid bias towards majority samples. We evaluate our approach on two common benchmark datasets and compare our hierarchical approach against a flat learning setup. We also conduct a comparison between sequence-to-sequence and memory-to-sequence learning models. Experiments show that our hierarchical approach overcomes issues of data sparsity and learns robust lexico-syntactic patterns, consistently outperforming flat baselines and previous work by up to 30%. We also find that while memory-to-sequence models can outperform sequence-to-sequence models in some cases, the latter are generally more stable in their performance and represent a safer overall choice.

Citation

Dethlefs, N., Schoene, A., & Cuayáhuitl, H. (2021). A divide-and-conquer approach to neural natural language generation from structured data. Neurocomputing, 433, 300-309. https://doi.org/10.1016/j.neucom.2020.12.083

Journal Article Type Article
Acceptance Date Dec 14, 2020
Online Publication Date Jan 5, 2021
Publication Date Apr 14, 2021
Deposit Date Feb 1, 2021
Publicly Available Date Mar 28, 2024
Journal Neurocomputing
Print ISSN 0925-2312
Electronic ISSN 1872-8286
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 433
Pages 300-309
DOI https://doi.org/10.1016/j.neucom.2020.12.083
Keywords Neural networks; Artificial intelligence; Natural language processing
Public URL https://hull-repository.worktribe.com/output/3709268
Publisher URL https://www.sciencedirect.com/science/article/abs/pii/S0925231220319950?via%3Dihub

Files






You might also like



Downloadable Citations