Structural Realization with GGNNs

Jinman Zhao, Gerald Penn, Huan Ling


Abstract
In this paper, we define an abstract task called structural realization that generates words given a prefix of words and a partial representation of a parse tree. We also present a method for solving instances of this task using a Gated Graph Neural Network (GGNN). We evaluate it with standard accuracy measures, as well as with respect to perplexity, in which its comparison to previous work on language modelling serves to quantify the information added to a lexical selection task by the presence of syntactic knowledge. That the addition of parse-tree-internal nodes to this neural model should improve the model, with respect both to accuracy and to more conventional measures such as perplexity, may seem unsurprising, but previous attempts have not met with nearly as much success. We have also learned that transverse links through the parse tree compromise the model’s accuracy at generating adjectival and nominal parts of speech.
Anthology ID:
2021.textgraphs-1.11
Volume:
Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)
Month:
June
Year:
2021
Address:
Mexico City, Mexico
Venues:
NAACL | TextGraphs
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
115–124
Language:
URL:
https://aclanthology.org/2021.textgraphs-1.11
DOI:
10.18653/v1/2021.textgraphs-1.11
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.textgraphs-1.11.pdf
Data
Penn Treebank