AggGen: Ordering and Aggregating while Generating

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10440587" target="_blank" >RIV/00216208:11320/21:10440587 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2021.acl-long.113" target="_blank" >https://aclanthology.org/2021.acl-long.113</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2021.acl-long.113" target="_blank" >10.18653/v1/2021.acl-long.113</a>

Result language

angličtina

Original language name

AggGen: Ordering and Aggregating while Generating

Original language description

We present AggGen (pronounced &apos;again&apos;) a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still end-to-end: AggGen performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/AggGen.

Czech name

—

Czech description

—

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)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2021

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing

ISBN

978-1-954085-52-7

ISSN

—

e-ISSN

—

Number of pages

16

Pages from-to

1419-1434

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg, PA, USA

Event location

Online

Event date

Aug 2, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—