Team Iterate @ AutoMin 2023 - Experiments with Iterative Minuting
The result's identifiers
Result code in 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>
Result on the web
<a href="https://aclanthology.org/2023.inlg-genchal.16/" target="_blank" >https://aclanthology.org/2023.inlg-genchal.16/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Team Iterate @ AutoMin 2023 - Experiments with Iterative Minuting
Original language description
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.
Czech name
—
Czech description
—
Classification
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)
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 16th International Natural Language Generation Conference: System Demonstrations
ISBN
979-8-89176-003-5
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
114-120
Publisher name
Association for Computational Linguistics
Place of publication
Prague, Czechia
Event location
Prague, Czechia
Event date
Oct 11, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—