MétaCan
Menu
Back to cohort
Record W4402747380 · doi:10.23977/acss.2024.080603

Research on Graph-based Text Summarization Extraction Algorithm

2024· article· en· W4402747380 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.

venuePublished in a venue whose home country is Canada.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueAdvances in Computer Signals and Systems · 2024
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Text Analysis Techniques
Canadian institutionsnot available
Fundersnot available
KeywordsAutomatic summarizationComputer scienceGraphText graphArtificial intelligenceNatural language processingInformation retrievalAlgorithmTheoretical computer science

Abstract

fetched live from OpenAlex

This paper proposes a graph-based text summarization extraction algorithm. The algorithm is based on directed graphs and can incorporate the position information of sentences into the computational scope. When calculating the edge weights of nodes in the directed graph, a pre-trained model after negative sampling is used, which not only can extract deeper semantic features but also enable higher relevance between the contextual sentences in the article. The algorithm also introduces a weighting mechanism to adjust the extraction priority of the sentences according to the article's theme, resulting in a higher quality of extracted summary sentences that can represent the key information of the text as much as possible. The algorithm can capture the key information in the text, reduce the impact of irrelevant information on semantics, and play a role in text compression.

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)0.000
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: Methods · Consensus signal: none
Teacher disagreement score0.904
Threshold uncertainty score0.652

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.002
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0000.000
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 head0.040
GPT teacher head0.384
Teacher spread0.345 · 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