Abstrakt
In this article, we report the findings of the second shared task on Automatic Minuting (AutoMin) held as a Generation Challenge at the 16th International Natural Language Generation (INLG) Conference 2023. The second Automatic Minuting shared task is a successor to the first AutoMin which took place in 2021.
The primary objective of the Au- toMin shared task is to garner participation of the speech and natural language process- ing and generation community to create au- tomatic methods for generating minutes from multi-party meetings. Five teams from diverse backgrounds participated in the shared task this year.
A lot has changed in the Genera- tive AI landscape since the last AutoMin espe- cially with the emergence and wide adoption of Large Language Models (LLMs) to differ- ent downstream tasks. Most of the contribu- tions are based on some form of an LLM and we are also adding current outputs of GPT- 4 as a benchmark.
Furthermore, we examine the applicability of GPT-4 for automatic scor- ing of minutes. Compared to the previous in- stance of AutoMin, we also add another do- main, the minutes for EU Parliament sessions, and we experiment with a more fine-grained manual evaluation.
More details on the event can be found at https://ufal.github.io/ automin-2023/.