A Statistical, Grammar-Based Approach to Micro-Planning

Claire Gardent 1 Laura Perez-Beltrachini 1
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : While 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 micro-planning between aggregation, surface realization and sentence segmentation. In this paper, we propose a hybrid symbolic/statistical approach to jointly model 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-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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [40 references]  Display  Hide  Download

https://hal.inria.fr/hal-01623758
Contributor : Claire Gardent <>
Submitted on : Wednesday, October 25, 2017 - 4:01:19 PM
Last modification on : Friday, March 1, 2019 - 2:41:11 PM
Long-term archiving on : Friday, January 26, 2018 - 3:20:25 PM

File

submission2.pdf
Files produced by the author(s)

Identifiers

Citation

Claire Gardent, Laura Perez-Beltrachini. A Statistical, Grammar-Based Approach to Micro-Planning. Computational Linguistics, Massachusetts Institute of Technology Press (MIT Press), 2017, ⟨10.1162/COLI_a_00273⟩. ⟨hal-01623758⟩

Share

Metrics

Record views

135

Files downloads

125