MétaCan
Menu
Back to cohort

A Hybrid Continual Learning Approach for Efficient Hierarchical Classification of IT Support Tickets in the Presence of Class Overlap

2023· article· en· W4379983287 on OpenAlex
Yasmen Wahba, Nazim H. Madhavji, John Steinbacher

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicData Stream Mining Techniques
Canadian institutionsIBM (Canada)Western University
Fundersnot available
KeywordsComputer scienceClass hierarchyHierarchyTask (project management)InferenceArtificial intelligenceMachine learningClass (philosophy)TicketMulticlass classificationKey (lock)Data miningSupport vector machineComputer security

Abstract

fetched live from OpenAlex

A support ticket describes an issue faced by a system's end-users when they encounter issues with their system. For large-scale IT corpora with hundreds of classes organized in a hierarchy, the task of classifying support tickets is vital to guarantee long-term clients. Due to the complexity of the unstructured nature of human language, text classification is challenging. The task is even harder when classes overlap. In the business world, an efficient and interpretable ML model is preferred over an expensive black-box model. In this paper, we propose a Hybrid Online Offline Model (HOOM) for efficient classification of hierarchical text documents using linear ML models. The experimental results on a private dataset of IT support tickets show that the hybrid model (HOOM) exhibits a promising performance if deployed in a real-world scenario. Furthermore, the hybrid model is anticipated to have a fast inference time given the underlying linear classifiers.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.973
Threshold uncertainty score0.268

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.045
GPT teacher head0.306
Teacher spread0.261 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations4
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicData Stream Mining TechniquesFrench-language works237,207