MétaCan
Menu
Back to cohort
Record W3154476213 · doi:10.18653/v1/2021.cmcl-1.9

TorontoCL at CMCL 2021 Shared Task: RoBERTa with Multi-Stage Fine-Tuning for Eye-Tracking Prediction

2021· article· en· W3154476213 on OpenAlexafffund
Bai Li, Frank Rudzicz

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsVector InstituteUniversity of Toronto
FundersCanadian Institute for Advanced Research
KeywordsComputer scienceTransformerEye trackingTask (project management)Ranking (information retrieval)Artificial intelligenceComprehensionLanguage modelNatural language processingTracking (education)Reading comprehensionTask analysisMachine learningReading (process)Programming languageEngineering

Abstract

fetched live from OpenAlex

Eye movement data during reading is a useful source of information for understanding language comprehension processes.In this paper, we describe our submission to the CMCL 2021 shared task on predicting human reading patterns.Our model uses RoBERTa with a regression layer to predict 5 eye-tracking features.We train the model in two stages: we first finetune on the Provo corpus (another eye-tracking dataset), then fine-tune on the task data.We compare different Transformer models and apply ensembling methods to improve the performance.Our final submission achieves a MAE score of 3.929, ranking 3rd place out of 13 teams that participated in this shared 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.

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)0.013
metaresearch head score (Gemma)0.032
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 score0.045
Threshold uncertainty score0.096

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0130.032
Meta-epidemiology (narrow)0.0080.002
Meta-epidemiology (broad)0.0050.004
Bibliometrics0.0030.002
Science and technology studies0.0030.001
Scholarly communication0.0060.005
Open science0.0070.007
Research integrity0.0080.007
Insufficient payload (model declined to judge)0.0290.047

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 head0.046
GPT teacher head0.292
Teacher spread0.246 · 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

Citations13
Published2021
Admission routes2
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207