MétaCan
Menu
Back to cohort

Deep Learning for Recognizing the Anatomy of Tables on Datasheets

2019· article· en· W3003627710 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

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicCurrency Recognition and Detection
Canadian institutionsUniversity of Ottawa
Fundersnot available
KeywordsComputer scienceTable (database)SegmentationTask (project management)Artificial intelligenceMachine learningDeep learningMarket segmentationPattern recognition (psychology)Data miningEngineering

Abstract

fetched live from OpenAlex

With the growth of information flow through supply chains, we address the issue of semantically segmenting tabular data from document flows. This challenge is abstract in definition as there is no guideline to what defines a table, therefore we primarily applied deep learning methods to compare performances, as well as a morphology-based method to compare several methods for the task of table structure detection. Taking advantage of transfer learning, we found that Mask-RCNN was the most capable network at abstracting to segmentation of tables. Due to the large variation in sizes between columns and rows, most networks failed to detect both with equal effectiveness. However with Mask-RCNN 97.01% precision and 98.28% recall were attained, which put it far ahead of other models in row detection, cementing Mask-RCNN as the most effective choice in this task.

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 categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.981
Threshold uncertainty score0.133

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
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 head0.030
GPT teacher head0.286
Teacher spread0.256 · 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

Citations8
Published2019
Admission routes1
Has abstractyes

Explore more

Same topicCurrency Recognition and DetectionFrench-language works237,207