Spell: Streaming Parsing of System Event Logs

By Min Du, Feifei Li. Industrial Conference on Data Mining, 2016

441 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Log-based Anomaly Detection Without Log Parsing (2021, methodology): “For example, DeepLog [5] first applies the Spell [27] parser to extract log templates.”
LogBERT: Log Anomaly Detection via BERT (2021, methodology): “Research in [3, 22, 25, 37] extract log sequences by one of three windowing techniques, fixed window, sliding window, and session window.”
Tools and Benchmarks for Automated Log Parsing (2018, methodology): “3) Heuristics: By observing the characteristics of log messages, researchers proposed some log parsing methods (i.e., AEL [45], IPLoM [22], Spell [24], Drain [25]) based on heuristic rules.”
DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning (2017, methodology): “…by concurrent processes to separate, single-thread sequential sequences [22, 39, 42, 45]. state-of-the-art log parsing method is represented by Spell [9], an unsupervised streaming parser that parses incoming log entries in an online fashion based on the idea of LCS (longest common subsequence).”
Drain: An Online Log Parsing Approach with Fixed Depth Tree (2017, methodology): “For SHISO and Spell, the depth of the parse tree could increase during the parsing process.”