Spelling Corrector for Turkish Product Search
Bibliographic record
Abstract
Spell correction for e-commerce platforms presents unique challenges that are not adequately addressed by existing methods, which are primarily tailored for general purpose. These challenges include handling specialized terminology, brand names, and foreign terms frequently used in search queries. Traditional spell correction algorithms often fail to account for these complexities, leading to irrelevant search results and decreased user satisfaction. This study aims to develop and evaluate a novel spell correction algorithm specifically designed for the Turkish e-commerce context, with a focus on online food and grocery search queries. To enhance the spell correction process, we developed a two-module system consisting of a suggester and a ranker. The suggester module, leveraging TURNA, a pretrained transformer-based Turkish model, is designed to generate possible corrections by capturing the complex relationships within Turkish language data using spelling mistake weights derived from custom Turkish datasets. The ranker module then ranks these suggestions using various domain-specific features. Experimental results show that the proposed model successfully improves spell correction performance in the e-commerce domain, outperforming existing tools. However, the model's performance in general Turkish text correction is less effective, indicating areas for further refinement.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.008 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".