klinger.bib
@inproceedings{Bagdon2024,
author = {Christopher Bagdon and Prathamesh Karmalkar and Harsha Gurulingappa and Roman Klinger},
title = {"You are an expert annotator": Automatic Best–Worst-Scaling Annotations for Emotion Intensity Modeling},
booktitle = {Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
year = {2024},
month = {June},
address = {Mexico City, Mexico},
publisher = {Association for Computational Linguistics},
note = {accepted},
internaltype = {conferenceproc},
url = {https://www.romanklinger.de/publications/BagdonNAACL2024.pdf}
}
@article{Wuehrl2024b,
author = {Amelie W\"uhrl and Dustin Wright and Roman Klinger and Isabelle Augenstein},
title = {Understanding Fine-grained Distortions in Reports of Scientific Findings},
journal = {ArXiv e-prints},
archiveprefix = {arXiv},
eprint = {2402.12431},
primaryclass = {cs.CL},
keywords = {Computer Science - Computation and Language},
year = 2024,
note = {preprint},
archiveprefix = {arXiv},
eprint = {2402.12431},
pdf = {https://arxiv.org/pdf/2402.12431.pdf},
internaltype = {preprint}
}
@inproceedings{Wemmer2024,
author = {Eileen Wemmer and Sofie Labat and Roman Klinger},
title = {EmoProgress: Cumulated Emotion Progression Analysis in Dreams and Customer Service Dialogues},
booktitle = {Proceedings of the the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING)},
year = {2024},
address = {Turin, Italy},
internaltype = {conferenceproc},
note = {accepted},
url = {https://www.romanklinger.de/publications/WemmerLabatKlingerLRECCOLING2024.pdf}
}
@inproceedings{Velutharambath2024,
author = {Aswathy Velutharambath and Amelie W\"uhrl and Roman
Klinger},
title = {Can Factual Statements be Deceptive? The DeFaBel
Corpus of Belief-based Deception},
booktitle = {Proceedings of the the 2024 Joint International
Conference on Computational Linguistics, Language
Resources and Evaluation (LREC-COLING)},
year = {2024},
address = {Turin, Italy},
internaltype = {conferenceproc},
note = {accepted},
pdf = {https://www.romanklinger.de/publications/VelutharambathWuehrlKlinger-LREC-COLING2024.pdf},
eprint = {2403.10185},
archiveprefix = {arXiv},
primaryclass = {cs.CL}
}
@inproceedings{Barreiss2024,
author = {Patrick Barreiß and Roman Klinger and Jeremy Barnes},
title = {English Prompts are Better for {NLI}-based Zero-Shot
Emotion Classification than Target-Language Prompts},
year = {2024},
publisher = {Association for Computing Machinery},
location = {Singapore},
booktitle = {Companion Proceedings of the ACM Web Conference
2024},
series = {WWW '24 Companion},
url = {https://arxiv.org/abs/2402.03223},
internaltype = {workshop}
}
@inproceedings{wegge-klinger-2024-topic,
title = {Topic Bias in Emotion Classification},
author = {Wegge, Maximilian and Klinger, Roman},
editor = {van der Goot, Rob and Bak, JinYeong and
M{\"u}ller-Eberstein, Max and Xu, Wei and Ritter,
Alan and Baldwin, Tim},
booktitle = {Proceedings of the Ninth Workshop on Noisy and
User-generated Text (W-NUT 2024)},
month = mar,
year = {2024},
address = {San {\.G}iljan, Malta},
publisher = {Association for Computational Linguistics},
url = {https://aclanthology.org/2024.wnut-1.9},
pages = {89--103},
abstract = {Emotion corpora are typically sampled based on
keyword/hashtag search or by asking study
participants to generate textual instances. In any
case, these corpora are not uniform samples
representing the entirety of a domain. We
hypothesize that this practice of data acquision
leads to unrealistic correlations between
overrepresented topics in these corpora that harm
the generalizability of models. Such topic bias
could lead to wrong predictions for instances like
{``}I organized the service for my aunt{'}s
funeral.{''} when funeral events are overpresented
for instances labeled with sadness, despite the
emotion of pride being more appropriate here. In
this paper, we study this topic bias both from the
data and the modeling perspective. We first label a
set of emotion corpora automatically via topic
modeling and show that emotions in fact correlate
with specific topics. Further, we see that emotion
classifiers are confounded by such topics. Finally,
we show that the established debiasing method of
adversarial correction via gradient reversal
mitigates the issue. Our work points out issues with
existing emotion corpora and that more
representative resources are required for fair
evaluation of models predicting affective concepts
from text.},
internaltype = {workshop},
pdf = {https://www.romanklinger.de/publications/WeggeKlinger2024.pdf},
eprint = {2312.09043},
archiveprefix = {arXiv},
primaryclass = {cs.CL}
}
@inproceedings{wuehrl-etal-2024-makes,
title = {What Makes Medical Claims (Un)Verifiable? Analyzing
Entity and Relation Properties for Fact
Verification},
author = {Wührl, Amelie and Menchaca Resendiz, Yarik and
Grimminger, Lara and Klinger, Roman},
editor = {Graham, Yvette and Purver, Matthew},
booktitle = {Proceedings of the 18th Conference of the European
Chapter of the Association for Computational
Linguistics (Volume 1: Long Papers)},
month = mar,
year = {2024},
address = {St. Julian{'}s, Malta},
publisher = {Association for Computational Linguistics},
url = {https://aclanthology.org/2024.eacl-long.124},
pages = {2046--2058},
abstract = {Verifying biomedical claims fails if no evidence can
be discovered. In these cases, the fact-checking
verdict remains unknown and the claim is
unverifiable. To improve this situation, we have to
understand if there are any claim properties that
impact its verifiability. In this work we assume
that entities and relations define the core
variables in a biomedical claim{'}s anatomy and
analyze if their properties help us to differentiate
verifiable from unverifiable claims. In a study with
trained annotation experts we prompt them to find
evidence for biomedical claims, and observe how they
refine search queries for their evidence
search. This leads to the first corpus for
scientific fact verification annotated with
subject{--}relation{--}object triplets, evidence
documents, and fact-checking verdicts (the BEAR-FACT
corpus). We find (1) that discovering evidence for
negated claims (e.g., X{--}does-not-cause{--}Y) is
particularly challenging. Further, we see that
annotators process queries mostly by adding
constraints to the search and by normalizing
entities to canonical names. (2) We compare our
in-house annotations with a small crowdsourcing
setting where we employ both medical experts and
laypeople. We find that domain expertise does not
have a substantial effect on the reliability of
annotations. Finally, (3), we demonstrate that it is
possible to reliably estimate the success of
evidence retrieval purely from the claim text
(.82F$_1$), whereas identifying unverifiable claims
proves more challenging (.27F$_1$)},
pdf = {https://www.romanklinger.de/publications/Wuehrl-etal-2024-EACL.pdf},
eprint = {2402.01360},
archiveprefix = {arXiv},
primaryclass = {cs.CL},
internaltype = {conferenceproc}
}