MétaCan
Menu
Back to cohort
Record W2295712623

ualberta at TAC-KBP 2012: English and Cross-Lingual Entity Linking.

2012· article· en· W2295712623 on OpenAlexaffvenue
Zhaochen Guo, Ying Xu, Filipe Mesquita, Denilson Barbosa, Grzegorz Kondrak

Bibliographic record

VenueTheory and applications of categories · 2012
Typearticle
Languageen
FieldDecision Sciences
TopicData Quality and Management
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsComputer scienceEntity linkingKnowledge baseAmbiguityInformation retrievalConstruct (python library)Task (project management)Information extractionPaceNatural language processingArtificial intelligenceProgramming languageEngineering
DOInot available

Abstract

fetched live from OpenAlex

On one hand, the proliferation of the Web has generated massive information in an unorganized way and is still growing in an accelerating pace. On the other hand, structured and queryable knowledge bases are very difficult to construct and update. Automatic knowledge base construction techniques are greatly needed to convert the rich Web information into useful knowledge bases. Besides information extraction, ambiguities about entities and facts also need to be resolved. Entity Linking, which links an extracted named entity to an entity in a knowledge base, is to solve this ambiguity before populating knowledge. In this paper, we describe ualberta’s system for the 2012 TAC-KBP English and Cross-Lingual Entity Linking (EL) task, and report the result on the evaluation datasets.

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.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.006
metaresearch head score (Gemma)0.021
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.081
Threshold uncertainty score0.162

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0060.021
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0070.008
Science and technology studies0.0030.001
Scholarly communication0.0040.007
Open science0.0030.005
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0190.014

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 head0.375
Teacher spread0.331 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations5
Published2012
Admission routes2
Has abstractyes

Explore more

Same venueTheory and applications of categoriesSame topicData Quality and ManagementFrench-language works237,207