Generating Diverse Descriptions from Semantic Graphs

Jiuzhou Han, Daniel Beck, Trevor Cohn


Abstract
Text generation from semantic graphs is traditionally performed with deterministic methods, which generate a unique description given an input graph. However, the generation problem admits a range of acceptable textual outputs, exhibiting lexical, syntactic and semantic variation. To address this disconnect, we present two main contributions. First, we propose a stochastic graph-to-text model, incorporating a latent variable in an encoder-decoder model, and its use in an ensemble. Second, to assess the diversity of the generated sentences, we propose a new automatic evaluation metric which jointly evaluates output diversity and quality in a multi-reference setting. We evaluate the models on WebNLG datasets in English and Russian, and show an ensemble of stochastic models produces diverse sets of generated sentences while, retaining similar quality to state-of-the-art models.
Anthology ID:
2021.inlg-1.1
Volume:
Proceedings of the 14th International Conference on Natural Language Generation
Month:
August
Year:
2021
Address:
Aberdeen, Scotland, UK
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–11
Language:
URL:
https://aclanthology.org/2021.inlg-1.1
DOI:
Bibkey:
Cite (ACL):
Jiuzhou Han, Daniel Beck, and Trevor Cohn. 2021. Generating Diverse Descriptions from Semantic Graphs. In Proceedings of the 14th International Conference on Natural Language Generation, pages 1–11, Aberdeen, Scotland, UK. Association for Computational Linguistics.
Cite (Informal):
Generating Diverse Descriptions from Semantic Graphs (Han et al., INLG 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.inlg-1.1.pdf
Code
 Jiuzhouh/Multi-Score
Data
WebNLG