MétaCan
Menu
Back to cohort
Record W4385572106 · doi:10.18653/v1/2023.semeval-1.7

BERTastic at SemEval-2023 Task 3: Fine-Tuning Pretrained Multilingual Transformers Does Order Matter?

2023· article· en· W4385572106 on OpenAlexaff
Tarek M. Mahmoud, Preslav Nakov

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsComputer scienceTransformerArtificial intelligenceFine-tuningSemEvalDeep learningLanguage modelNatural language processingMachine learningFraming (construction)Task (project management)

Abstract

fetched live from OpenAlex

The naive approach for fine-tuning pretrained deep learning models on downstream tasks involves feeding them mini-batches of randomly sampled data. In this paper, we propose a more elaborate method for fine-tuning Pretrained Multilingual Transformers (PMTs) on multilingual data. Inspired by the success of curriculum learning approaches, we investigate the significance of fine-tuning PMTs on multilingual data in a sequential fashion language by language. Unlike the curriculum learning paradigm where the model is presented with increasingly complex examples, we do not adopt a notion of “easy” and “hard” samples. Instead, our experiments draw insight from psychological findings on how the human brain processes new information and the persistence of newly learned concepts. We perform our experiments on a challenging news-framing dataset that contains texts in six languages. Our proposed method outperforms the naïve approach by achieving improvements of 2.57\% in terms of F1 score. Even when we supplement the naïve approach with recency fine-tuning, we still achieve an improvement of 1.34\% with a 3.63\%$ convergence speed-up. Moreover, we are the first to observe an interesting pattern in which deep learning models exhibit a human-like primacy-recency effect.

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 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 categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.894
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.001

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 head0.263
Teacher spread0.245 · 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 teacher head, not a consensus.

Study designSimulation or modeling
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

Citations1
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207