MétaCan
Menu
Back to cohort
Record W1988996388 · doi:10.5555/777092.777258

Generalized features: their application to classification

2002· article· en· W1988996388 on OpenAlex

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

VenueNational Conference on Artificial Intelligence · 2002
Typearticle
Languageen
FieldComputer Science
TopicText and Document Classification Technologies
Canadian institutionsUniversity of Ottawa
Fundersnot available
KeywordsComputer sciencesortFocus (optics)Set (abstract data type)Feature (linguistics)Process (computing)Artificial intelligenceMachine learningInformation retrievalData mining

Abstract

fetched live from OpenAlex

Classification learning algorithms in general, and text classification methods in particular, tend to focus on features of individual training examples, rather than on the relationships between the examples. However, in many situations a set of items contains more information than just feature values of individual items. For example, taking into account the articles that are cited by or cite an article in question would increase our chances of correct classification. We propose to recognize and put in use generalized features (or set features), which describe a training example, but depend on the dataset as a whole, with the goal of achieving better classification accuracy. Although the idea of generalized features is consistent with the objectives of relational learning (ILP), we feel that instead of using the computationally heavy and conceptually general ILP methods, there may be a benefit in looking for approaches that use specific relations between texts, and in particular, between emails. Generalized features are the way to capture the information that lies beyond a particular item, the information that combines the dataset in some sort of structure. Different datasets have different structures, but we could guess what kind of information would be useful for classification. It is similar to the process of choosing relevant features. For example, we can guess that the references are relevant to the topic of an article, but the relative length is not. There have been some attempts to include additional information about a dataset to the standard classification process based on plain features. One example is using references to classify technical articles and hyperlinks to classify web pages. This research shows that some links could be confusing while others are very helpful. Another example is character recognition. The recognition process can be based not only on the shape of a character, but also on preceding characters and even preceding words. Our attention is focused on the email classification problem. Nowadays, when a typical user receives about 4050 email messages daily, there is a great need in automatic classification systems that could sort, archive, and filter messages accurately. Typically, people work with emails as with general texts and base the classification decisions on the words that appear in the header and in the body of an

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.982
Threshold uncertainty score0.998

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.003

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 head0.169
GPT teacher head0.343
Teacher spread0.174 · 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