Neural Pipeline for Zero-Shot Data-to-Text Generation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A10457007" target="_blank" >RIV/00216208:11320/22:10457007 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2022.acl-long.271/" target="_blank" >https://aclanthology.org/2022.acl-long.271/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2022.acl-long.271" target="_blank" >10.18653/v1/2022.acl-long.271</a>
Alternative languages
Result language
angličtina
Original language name
Neural Pipeline for Zero-Shot Data-to-Text Generation
Original language description
In data-to-text (D2T) generation, training on in-domain data leads to overfitting to the data representation and repeating training data noise. We examine how to avoid finetuning pretrained language models (PLMs) on D2T generation datasets while still taking advantage of surface realization capabilities of PLMs. Inspired by pipeline approaches, we propose to generate text by transforming single-item descriptions with a sequence of modules trained on general-domain text-based operations: ordering, aggregation, and paragraph compression. We train PLMs for performing these operations on a synthetic corpus WikiFluent which we build from English Wikipedia. Our experiments on two major triple-to-text datasets - WebNLG and E2E - show that our approach enables D2T generation from RDF triples in zero-shot settings.
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
2022
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 60th Annual Meeting of the Association for Computational Linguistics: ACL 2022
ISBN
978-1-955917-21-6
ISSN
—
e-ISSN
—
Number of pages
19
Pages from-to
3914-3932
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Dublin, Ireland
Event date
May 22, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—