Data-to-Text Generation with Iterative Text Editing
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10424454" target="_blank" >RIV/00216208:11320/20:10424454 - isvavai.cz</a>
Result on the web
<a href="https://www.aclweb.org/anthology/2020.inlg-1.9/" target="_blank" >https://www.aclweb.org/anthology/2020.inlg-1.9/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Data-to-Text Generation with Iterative Text Editing
Original language description
We present a novel approach to data-to-text generation based on iterative text editing. Our approach maximizes the completeness and semantic accuracy of the output text while leveraging the abilities of recent pretrained models for text editing (LaserTagger) and language modelling (GPT-2) to improve the text fluency. To this end, we first transform data to text using trivial per-item lexicalizations, iteratively improving the resulting text by a neural model trained for the sentence fusion task. The model output is filtered by a simple heuristic and reranked with an off-the-shelf pretrained language model. We evaluate our approach on two major data-to-text datasets (WebNLG, Cleaned E2E) and analyze its caveats and benefits. Furthermore, we show that our formulation of data-to-text generation opens up the possibility for zero-shot domain adaptation using a general-domain dataset for sentence fusion.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 13th International Conference on Natural Language Generation (INLG 2020)
ISBN
978-1-952148-54-5
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
60-67
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburgh, PA, USA
Event location
Online
Event date
Dec 15, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—