MétaCan
Menu
Back to cohort
Record W4293863204 · doi:10.1109/siu55565.2022.9864782

Annotation of Financial Entities Using A Comprehensive Scheme in Turkish

2022· article· en· W4293863204 on OpenAlex
Kubra Adali, A. Cüneyd Tantuğ

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

Venue2022 30th Signal Processing and Communications Applications Conference (SIU) · 2022
Typearticle
Languageen
FieldDecision Sciences
TopicStock Market Forecasting Methods
Canadian institutionsStantec (Canada)
Fundersnot available
KeywordsComputer scienceTurkishNatural language processingAnnotationArtificial intelligenceInformation extractionTask (project management)ScarcityNamed-entity recognitionBaseline (sea)Language modelQuality (philosophy)Distributional semanticsDomain (mathematical analysis)Stock marketInformation retrievalContext (archaeology)Semantic similarityLinguistics

Abstract

fetched live from OpenAlex

Information extraction (IE) which refers to the task of turning texts into structured form is also employed in finance domain for extraction of information which have a big importance for different financial concepts such as market, stock, and indices etc. As many other applications in Natural Language Processing(NLP), annotated corpora which involves entities, that represent characteristics of the related domain, is also essential resources for training and evaluation of IE models. Unfortunately, the creation of these resources is rather thorny, thus the scarcity of annotated language resources is one of the most prominent problems for lesser-studied language; as in the case for Turkish. In this paper, we present an ontology of financial concepts, and an effort to produce a high-quality corpus which includes 500 news documents annotated with these concepts in Turkish. We employ the dataset in the training of a baseline entity recognition model, and performance achieved over the dataset is 64.5% F-scores.

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)0.002
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: Empirical
Teacher disagreement score0.913
Threshold uncertainty score0.996

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.002
Science and technology studies0.0010.001
Scholarly communication0.0000.000
Open science0.0020.001
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 head0.195
GPT teacher head0.413
Teacher spread0.218 · 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