2026.bib
@inproceedings{dangendorf-etal-2026-extracting,
title = {Extracting Multi-Word Expressions Representing Technical Terms and Proper Nouns in Log Messages},
author = {Dangendorf, Kilian and
H{\"a}nsel, Sven-Ove and
Rosendahl, Jannik and
Heine, Felix and
Kleiner, Carsten and
Wartena, Christian},
editor = {Ojha, Atul Kr. and
Mititelu, Verginica Barbu and
Constant, Mathieu and
Stoyanova, Ivelina and
Do{\u{g}}ru{\"o}z, A. Seza and
Rademaker, Alexandre},
booktitle = {Proceedings of the 22nd Workshop on Multiword Expressions ({MWE} 2026)},
month = mar,
year = {2026},
address = {Rabat, Marocco},
publisher = {Association for Computational Linguistics},
url = {https://aclanthology.org/2026.mwe-1.7/},
doi = {10.18653/v1/2026.mwe-1.7},
pages = {61--65},
isbn = {979-8-89176-363-0},
abstract = {IT-systems generate log messages containing important information about the system{'}s health. To gather information about system entities, we extract technical terms and proper nouns as multi-word expressions (MWEs) from a wide range of log messages from 16 different real systems. We apply Gries' information-theoretic approach which iteratively calculates the best MWE candidates using an eight-dimensional ranking method. These candidates are evaluated in an annotation study, achieving a precision of 66 {\%}. This value is significantly higher than evaluations on general-purpose texts, demonstrating the higher occurrence of compound technical terms and proper nouns in log messages. The MWEs found can be used to reduce the number of nodes in a system behavior graph while increasing the information density of the nodes.}
}