Sequence-to-Sequence Models for Automated Log Parsing: Transformer and Mamba Outperform Traditional Approaches
A controlled empirical study comparing four sequence modelling architectures for automated log parsing found that Transformer models achieve the lowest parsing error, followed by Mamba, mono-LSTM, and bi-LSTM. The research evaluated 396 models across multiple dataset configurations using relative Levenshtein edit distance as the performance metric. The findings offer practical guidance for software engineers choosing architectures for log parsing under varying data and compute constraints.
Researchers conducted a systematic empirical study evaluating how architecture choice, tokenization, sequence length, and training data availability affect automated log parsing performance and computational cost. Four architectures were compared: Transformer, Mamba state-space, monodirectional LSTM, and bidirectional LSTM, with 396 models trained and assessed using relative Levenshtein edit distance. Transformers achieved the best mean relative edit distance of 0.111, reducing parsing error by 23.4% compared to alternatives, while Mamba scored 0.145 with substantially lower computational overhead. Character-level tokenization generally improved performance across models, and sequence length had negligible practical impact on Transformer accuracy. Both Transformer and Mamba demonstrated stronger sample efficiency than recurrent models, making Mamba a compelling option when data or compute resources are limited. The study also includes a comparison with large language models in its updated version.
What's missing
The LLM comparison added in v2 is mentioned but not described in the abstract, leaving its scope and conclusions unclear. It is also not specified whether the computational cost measurements account for inference-time costs in addition to training, which is relevant for deployment decisions.
What different sources said
- arXiv cs.CLCenter
On Sequence-to-Sequence Models for Automated Log Parsing
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.