Sentence Packaging in Text Generation from Semantic Graphs as a Community Detection Problem

Alexander Shvets, Simon Mille, Leo Wanner


Abstract
An increasing amount of research tackles the challenge of text generation from abstract ontological or semantic structures, which are in their very nature potentially large connected graphs. These graphs must be “packaged” into sentence-wise subgraphs. We interpret the problem of sentence packaging as a community detection problem with post optimization. Experiments on the texts of the VerbNet/FrameNet structure annotated-Penn Treebank, which have been converted into graphs by a coreference merge using Stanford CoreNLP, show a high F1-score of 0.738.
Anthology ID:
W18-6542
Volume:
Proceedings of the 11th International Conference on Natural Language Generation
Month:
November
Year:
2018
Address:
Tilburg University, The Netherlands
Editors:
Emiel Krahmer, Albert Gatt, Martijn Goudbeek
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
350–359
Language:
URL:
https://aclanthology.org/W18-6542
DOI:
10.18653/v1/W18-6542
Bibkey:
Cite (ACL):
Alexander Shvets, Simon Mille, and Leo Wanner. 2018. Sentence Packaging in Text Generation from Semantic Graphs as a Community Detection Problem. In Proceedings of the 11th International Conference on Natural Language Generation, pages 350–359, Tilburg University, The Netherlands. Association for Computational Linguistics.
Cite (Informal):
Sentence Packaging in Text Generation from Semantic Graphs as a Community Detection Problem (Shvets et al., INLG 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6542.pdf