MétaCan
Menu
Back to cohort
Record W2598150924 · doi:10.1142/s2425038416300056

Methods and resources for computing semantic relatedness

2017· article· en· W2598150924 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

VenueEncyclopedia with Semantic Computing and Robotic Intelligence · 2017
Typearticle
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsToronto Metropolitan University
Fundersnot available
KeywordsWordNetComputer scienceInformation retrievalSemantic similarityKey (lock)Section (typography)Selection (genetic algorithm)Resource (disambiguation)Knowledge baseSimilarity (geometry)Representation (politics)Natural language processingArtificial intelligence

Abstract

fetched live from OpenAlex

Semantic relatedness (SR) is defined as a measurement that quantitatively identifies some form of lexical or functional association between two words or concepts based on the contextual or semantic similarity of those two words regardless of their syntactical differences. Section 1 of the entry outlines the working definition of SR and its applications and challenges. Section 2 identifies the knowledge resources that are popular among SR methods. Section 3 reviews the primary measurements used to calculate SR. Section 4 reviews the evaluation methodology which includes gold standard dataset and methods. Finally, Sec. 5 introduces further reading. In order to develop appropriate SR methods, there are three key aspects that need to be examined: (1) the knowledge resources that are used as the source for extracting SR; (2) the methods that are used to quantify SR based on the adopted knowledge resource; and (3) the datasets and methods that are used for evaluating SR techniques. The first aspect involves the selection of knowledge bases such as WordNet or Wikipedia. Each knowledge base has its merits and downsides which can directly affect the accuracy and the coverage of the SR method. The second aspect relies on different methods for utilizing the beforehand selected knowledge resources, for example, methods that depend on the path between two words, or a vector representation of the word. As for the third aspect, the evaluation for SR methods consists of two aspects, namely (1) the datasets that are used and (2) the various performance measurement methods. SR measures are increasingly applied in information retrieval to provide semantics between query and documents to reveal relatedness between non-syntactically-related content. Researchers have already applied many different information and knowledge sources in order to compute SR between two words. Empirical research has already shown that results of many of these SR techniques have reasonable correlation with human subjects interpretation of relatedness between two words.

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)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.961
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0020.000
Scholarly communication0.0010.000
Open science0.0010.001
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 head0.018
GPT teacher head0.333
Teacher spread0.315 · 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