A Statistical, Grammar-Based Approach to Microplanning

Claire Gardent, Laura Perez-Beltrachini


Abstract
Although there has been much work in recent years on data-driven natural language generation, little attention has been paid to the fine-grained interactions that arise during microplanning between aggregation, surface realization, and sentence segmentation. In this article, we propose a hybrid symbolic/statistical approach to jointly model the constraints regulating these interactions. Our approach integrates a small handwritten grammar, a statistical hypertagger, and a surface realization algorithm. It is applied to the verbalization of knowledge base queries and tested on 13 knowledge bases to demonstrate domain independence. We evaluate our approach in several ways. A quantitative analysis shows that the hybrid approach outperforms a purely symbolic approach in terms of both speed and coverage. Results from a human study indicate that users find the output of this hybrid statistic/symbolic system more fluent than both a template-based and a purely symbolic grammar-based approach. Finally, we illustrate by means of examples that our approach can account for various factors impacting aggregation, sentence segmentation, and surface realization.
Anthology ID:
J17-1001
Volume:
Computational Linguistics, Volume 43, Issue 1 - April 2017
Month:
April
Year:
2017
Address:
Cambridge, MA
Venue:
CL
SIG:
Publisher:
MIT Press
Note:
Pages:
1–30
Language:
URL:
https://aclanthology.org/J17-1001
DOI:
10.1162/COLI_a_00273
Bibkey:
Cite (ACL):
Claire Gardent and Laura Perez-Beltrachini. 2017. A Statistical, Grammar-Based Approach to Microplanning. Computational Linguistics, 43(1):1–30.
Cite (Informal):
A Statistical, Grammar-Based Approach to Microplanning (Gardent & Perez-Beltrachini, CL 2017)
Copy Citation:
PDF:
https://aclanthology.org/J17-1001.pdf