Semantic Accuracy in Natural Language Generation: A Thesis Proposal

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475849" target="_blank" >RIV/00216208:11320/23:10475849 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2023.acl-srw.48/" target="_blank" >https://aclanthology.org/2023.acl-srw.48/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2023.acl-srw.48" target="_blank" >10.18653/v1/2023.acl-srw.48</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Semantic Accuracy in Natural Language Generation: A Thesis Proposal

Popis výsledku v původním jazyce

With the fast-growing popularity of current large pre-trained language models (LLMs), it is necessary to dedicate efforts to making them more reliable. In this thesis proposal, we aim to improve the reliability of natural language generation systems (NLG) by researching the semantic accuracy of their outputs. We look at this problem from the outside (evaluation) and from the inside (interpretability). We propose a novel method for evaluating semantic accuracy and discuss the importance of working towards a unified and objective benchmark for NLG metrics. We also review interpretability approaches which could help us pinpoint the sources of inaccuracies within the models and explore potential mitigation strategies.

Název v anglickém jazyce

Semantic Accuracy in Natural Language Generation: A Thesis Proposal

Popis výsledku anglicky

With the fast-growing popularity of current large pre-trained language models (LLMs), it is necessary to dedicate efforts to making them more reliable. In this thesis proposal, we aim to improve the reliability of natural language generation systems (NLG) by researching the semantic accuracy of their outputs. We look at this problem from the outside (evaluation) and from the inside (interpretability). We propose a novel method for evaluating semantic accuracy and discuss the importance of working towards a unified and objective benchmark for NLG metrics. We also review interpretability approaches which could help us pinpoint the sources of inaccuracies within the models and explore potential mitigation strategies.

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

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)

ISBN

978-1-959429-69-2

ISSN

—

e-ISSN

—

Počet stran výsledku

10

Strana od-do

352-361

Název nakladatele

Association for Computational Linguistics

Místo vydání

Stroudsburg, PA, USA

Místo konání akce

Toronto, Canada

Datum konání akce

9. 7. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—