MétaCan
Menu
Back to cohort

Development of Language Model on Biomedical Domain to Pretrain Natural Language Processing

2024· article· en· W4400910582 on OpenAlexaff
Vijaya Gunturu, Yadavalli Devi Priya, Gayatri Vijayendra Bachhav, K. Praveena, R J Anandhi

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsHorizon College and Seminary
Fundersnot available
KeywordsComputer scienceNatural language processingDomain (mathematical analysis)Natural languageHuman–computer interactionArtificial intelligence

Abstract

fetched live from OpenAlex

Large neural language model like BERT can be pre trained to get extraordinary profits through multiple natural language processing task. Though, General Domain Corpora including web and news wire are focused on pre training efforts. The main specific pre training are benefited from general domain language models is considered as a prevailing assumption. The study focusses on the domain specific language model with abundance of unlabeled text like biomedical natural language processing and pre training from its scratch that results in more gains over the general domain language model. The investigation can be facilitated by compiling of biomedical NLP data sets that are publicly available. The experiment shows the pre training of domain specific model that act as a solid foundation in performing biomedical NLP task in wide range. the model is evaluated for modelling choices including task specific fine tuning and pre training. BERT models have some common practises involving named entity recognition using complex tagging schemes. The research can be accelerated with biomedical NLP for pre training and task specific model for the biomedical community and the leader board is created for biomedical language understanding and reasoning benchmark (BLURB).

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 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 score0.989
Threshold uncertainty score0.297

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 head0.015
GPT teacher head0.291
Teacher spread0.276 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207