Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking)

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10405564" target="_blank" >RIV/00216208:11320/19:10405564 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.aclweb.org/anthology/W19-8644/" target="_blank" >https://www.aclweb.org/anthology/W19-8644/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking)

Popis výsledku v původním jazyce

We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two different outputs. The latter is trained using pairwise hinge loss over scores from two copies of the rating network. We use learning to rank and synthetic data to improve the quality of ratings assigned by our system: we synthesise training pairs of distorted system outputs and train the system to rank the less distorted one higher. This leads to a 12% increase in correlation with human ratings over the previous benchmark. We also establish the state of the art on the dataset of relative rankings from the E2E NLG Challenge (Dušek et al., 2019), where synthetic data lead to a 4% accuracy increase over the base model.

Název v anglickém jazyce

Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking)

Popis výsledku anglicky

We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two different outputs. The latter is trained using pairwise hinge loss over scores from two copies of the rating network. We use learning to rank and synthetic data to improve the quality of ratings assigned by our system: we synthesise training pairs of distorted system outputs and train the system to rank the less distorted one higher. This leads to a 12% increase in correlation with human ratings over the previous benchmark. We also establish the state of the art on the dataset of relative rankings from the E2E NLG Challenge (Dušek et al., 2019), where synthetic data lead to a 4% accuracy increase over the base model.

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

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 12th International Conference on Natural Language Generation (INLG 2019)

ISBN

978-1-950737-94-9

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

369-376

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsubrgh, PA, USA

Místo konání akce

Tokyo, Japan

Datum konání akce

29. 10. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—