Saved in:
Bibliographic Details
Main Authors: Srivastava, Prerak, Corallo, Giulio, Rybalko, Sergey
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.01147
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915317871017984
author Srivastava, Prerak
Corallo, Giulio
Rybalko, Sergey
author_facet Srivastava, Prerak
Corallo, Giulio
Rybalko, Sergey
contents System-generated logs are typically converted into categorical log templates through parsing. These templates are crucial for generating actionable insights in various downstream tasks. However, existing parsers often fail to capture fine-grained template details, leading to suboptimal accuracy and reduced utility in downstream tasks requiring precise pattern identification. We propose a character-level log parser utilizing a novel neural architecture that aggregates character embeddings. Our approach estimates a sequence of binary-coded decimals to achieve highly granular log templates extraction. Our low-resource character-level parser, tested on revised Loghub-2k and a manually annotated industrial dataset, matches LLM-based parsers in accuracy while outperforming semantic parsers in efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01147
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Word is Worth 4-bit: Efficient Log Parsing with Binary Coded Decimal Recognition
Srivastava, Prerak
Corallo, Giulio
Rybalko, Sergey
Computation and Language
Machine Learning
System-generated logs are typically converted into categorical log templates through parsing. These templates are crucial for generating actionable insights in various downstream tasks. However, existing parsers often fail to capture fine-grained template details, leading to suboptimal accuracy and reduced utility in downstream tasks requiring precise pattern identification. We propose a character-level log parser utilizing a novel neural architecture that aggregates character embeddings. Our approach estimates a sequence of binary-coded decimals to achieve highly granular log templates extraction. Our low-resource character-level parser, tested on revised Loghub-2k and a manually annotated industrial dataset, matches LLM-based parsers in accuracy while outperforming semantic parsers in efficiency.
title A Word is Worth 4-bit: Efficient Log Parsing with Binary Coded Decimal Recognition
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2506.01147