AggGen: Ordering and Aggregating while Generating

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

AggGen: Ordering and Aggregating while Generating

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

AggGen: Ordering and Aggregating while Generating

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

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

—

Počet stran výsledku

16

Strana od-do

1419-1434

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Online

Datum konání akce

2. 8. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—