Team Iterate @ AutoMin 2023 - Experiments with Iterative Minuting

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475752" target="_blank" >RIV/00216208:11320/23:10475752 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2023.inlg-genchal.16/" target="_blank" >https://aclanthology.org/2023.inlg-genchal.16/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Team Iterate @ AutoMin 2023 - Experiments with Iterative Minuting

Popis výsledku v původním jazyce

This report describes the development of our system for automatic minuting created for the AutoMin 2023 Task A. As a baseline, we utilize a system based on the BART encoder-decoder model paired with a preprocessing pipeline similar to the one introduced by the winning solutions at AutoMin 2021. We then further explore the possibilities for iterative summarization by constructing an iterative minuting dataset from the provided data, finetuning on it and feeding the model previously generated minutes. We also experiment with adding more context by utilizing the Longformer encoder-decoder model and finetuning it on the SAMSum dataset. Our submitted solution is of the baseline approach, since we were unable to match its performance with our iterative variants. With the baseline, we achieve a ROUGE-1 score of 0.368 on the ELITR minuting corpus development set. We finally explore the performance of Vicuna 13B quantized language model for summarization.

Název v anglickém jazyce

Team Iterate @ AutoMin 2023 - Experiments with Iterative Minuting

Popis výsledku anglicky

This report describes the development of our system for automatic minuting created for the AutoMin 2023 Task A. As a baseline, we utilize a system based on the BART encoder-decoder model paired with a preprocessing pipeline similar to the one introduced by the winning solutions at AutoMin 2021. We then further explore the possibilities for iterative summarization by constructing an iterative minuting dataset from the provided data, finetuning on it and feeding the model previously generated minutes. We also experiment with adding more context by utilizing the Longformer encoder-decoder model and finetuning it on the SAMSum dataset. Our submitted solution is of the baseline approach, since we were unable to match its performance with our iterative variants. With the baseline, we achieve a ROUGE-1 score of 0.368 on the ELITR minuting corpus development set. We finally explore the performance of Vicuna 13B quantized language model for summarization.

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

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 16th International Natural Language Generation Conference: System Demonstrations

ISBN

979-8-89176-003-5

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

114-120

Název nakladatele

Association for Computational Linguistics

Místo vydání

Prague, Czechia

Místo konání akce

Prague, Czechia

Datum konání akce

11. 10. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—