Fine-Grained Control of Sentence Segmentation and Entity Positioning in Neural NLG

Kritika Mehta, Raheel Qader, Cyril Labbe, François Portet


Abstract
The move from pipeline Natural Language Generation (NLG) approaches to neural end-to-end approaches led to a loss of control in sentence planning operations owing to the conflation of intermediary micro-planning stages into a single model. Such control is highly necessary when the text should be tailored to respect some constraints such as which entity to be mentioned first, the entity position, the complexity of sentences, etc. In this paper, we introduce fine-grained control of sentence planning in neural data-to-text generation models at two levels - realization of input entities in desired sentences and realization of the input entities in the desired position among individual sentences. We show that by augmenting the input with explicit position identifiers, the neural model can achieve a great control over the output structure while keeping the naturalness of the generated text intact. Since sentence level metrics are not entirely suitable to evaluate this task, we used a metric specific to our task that accounts for the model’s ability to achieve control. The results demonstrate that the position identifiers do constraint the neural model to respect the intended output structure which can be useful in a variety of domains that require the generated text to be in a certain structure.
Anthology ID:
W19-8103
Volume:
Proceedings of the 1st Workshop on Discourse Structure in Neural NLG
Month:
November
Year:
2019
Address:
Tokyo, Japan
Venues:
INLG | WS
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
18–23
Language:
URL:
https://www.aclweb.org/anthology/W19-8103
DOI:
10.18653/v1/W19-8103
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W19-8103.pdf