Designing a Symbolic Intermediate Representation for Neural Surface Realization
Year: 2019
Type: conference-paper
Abstract: Generated output from neural NLG systems often contain errors such as hallucination, repetition or contradiction. This work focuses on designing a symbolic intermediate representation to be used in multi-stage neural generation with the intention of reducing the frequency of failed outputs. We show that surface realization from this intermediate representation is of high quality and when the full system is applied to the E2E dataset it outperforms the winner of the E2E challenge. Furthermore, by breaking out the surface realization step from typically end-to-end neural systems, we also provide a framework for non-neural content selection and planning systems to potentially take advantage of semi-supervised pretraining of neural surface realization models.
DOI: 10.18653/v1/w19-2308
Authors: Henry Elder, Jennifer Foster, James Barry, Alexander O’Connor
Institution: Dublin City University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W2946506877