Nataliia Kees


2022

pdf bib
Long Input Dialogue Summarization with Sketch Supervision for Summarization of Primetime Television Transcripts
Nataliia Kees | Thien Nguyen | Tobias Eder | Georg Groh
Proceedings of The Workshop on Automatic Summarization for Creative Writing

This paper presents our entry to the CreativeSumm 2022 shared task. Specifically tackling the problem of prime-time television screenplay summarization based on the SummScreen Forever Dreaming dataset. Our approach utilizes extended Longformers combined with sketch supervision including categories specifically for scene descriptions. Our system was able to produce the shortest summaries out of all submissions. While some problems with factual consistency still remain, the system was scoring highest among competitors in the ROUGE and BERTScore evaluation categories.

2021

pdf bib
Active Learning for Argument Strength Estimation
Nataliia Kees | Michael Fromm | Evgeniy Faerman | Thomas Seidl
Proceedings of the Second Workshop on Insights from Negative Results in NLP

High-quality arguments are an essential part of decision-making. Automatically predicting the quality of an argument is a complex task that recently got much attention in argument mining. However, the annotation effort for this task is exceptionally high. Therefore, we test uncertainty-based active learning (AL) methods on two popular argument-strength data sets to estimate whether sample-efficient learning can be enabled. Our extensive empirical evaluation shows that uncertainty-based acquisition functions can not surpass the accuracy reached with the random acquisition on these data sets.