MétaCan
Menu
Back to cohort
Record W3027907503 · doi:10.1007/s42979-020-00186-z

KuroNet: Regularized Residual U-Nets for End-to-End Kuzushiji Character Recognition

2020· article· en· W3027907503 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

VenueSN Computer Science · 2020
Typearticle
Languageen
FieldComputer Science
TopicHandwritten Text Recognition Techniques
Canadian institutionsUniversité de Montréal
Fundersnot available
KeywordsComputer scienceCursiveResidualArchitectureArtificial intelligenceOptical character recognitionCurriculumRegularization (linguistics)MetadataWorld Wide WebVisual artsArtAlgorithm

Abstract

fetched live from OpenAlex

Abstract Kuzushiji, a cursive writing style, had been used in Japan for over a thousand years starting from the eighth century. Over 3 million books on a diverse array of topics, such as literature, science, mathematics and even cooking are preserved. However, following a change to the Japanese writing system in 1900, Kuzushiji has not been included in regular school curricula. Therefore, most Japanese natives nowadays cannot read books written or printed just 150 years ago. Museums and libraries have invested a great deal of effort into creating digital copies of these historical documents as a safeguard against fires, earthquakes and tsunamis. The result has been datasets with hundreds of millions of photographs of historical documents which can only be read by a small number of specially trained experts. Thus there has been a great deal of interest in using machine learning to automatically recognize these historical texts and transcribe them into modern Japanese characters. Our proposed model KuroNet (which builds on Clanuwat et al. in International conference on document analysis and recognition (ICDAR), 2019) outperforms other model for Kuzushiji recognition. In this paper, KuroNet achieves higher accuracy while still recognizing entire pages of text using the residual U-Net architecture from adding more regularization. We also explore areas where our system is limited and suggests directions for future work.

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 categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.932
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0000.000
Scholarly communication0.0010.002
Open science0.0030.001
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 head0.040
GPT teacher head0.267
Teacher spread0.227 · 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