LexiTR is an innovative suite of tools specifically designed to enhance the analysis and understanding of the Turkish language.

A Turkish Lexicon Toolkit by TS Corpus

API Documentation
LexiTR is designed to fill the gap in Turkish vocabulary studies. It features an innovative suite of tools specifically designed to enhance the analysis and understanding of the Turkish language. LexiTR serves a rich dataset of 195,603,172 words spanning four genres

  academic papers
  social media
  fictional texts
  informative texts

Please cite the following paper if you use LexiTR Frequency Tool
 Sezer, T., & Karadağ, Ö. (2025). A Turkish Word Frequency Tool: LexiTR Frequency. Journal of Mother Tongue Education/Ana Dili Egitim Dergisi, 13(2).

Genre Percentage Number of words
Academic7.86%15,365,990
Social Media19.70%38,541,611
Fictional25.52%49,910,208
Informative46.92%91,785,363
Total:100.00%195,603,172
This diversity of genres and the size of the corpus ensures that users can access and analyze language patterns and usage across different styles and contexts. Each tool presented under LexiTR shares the same data source to set a valid research background.

Key Features of LexiTR:

    Collocationary: Explore how Turkish words co-occur in natural language with Turkish case-insensitive node matching, configurable genre and span filters, raw frequency counts, Mutual Information, positional association scores, and Direction Bias.
    Evidence-Based Collocation Analysis: Move from a ranked collocate list to positional heatmaps, genre profiles, and exact corpus attestations for selected L1-L5 and R1-R5 collocation cells.
    Frequency Tool: Gain quantitative insights with our frequency analysis, enabling you to determine how often words appear across different genres, aiding in everything from linguistic research to practical application in language learning.
    Reverse Dictionary: Search Turkish words by their endings to support work on rhyme, suffix behavior, morphology, and word-final sound patterns.
    API Access: Use documented endpoints for frequency lookup, collocation scores, collocate genre profiles, positional corpus attestations, and reverse dictionary searches.

LexiTR is more than just a toolset—it's an essential resource for educators, researchers, linguists, and enthusiasts of the Turkish language who are looking to deepen their understanding of linguistic patterns and improve their applications of the language in varied fields.
Whether you're crafting educational curriculum, conducting linguistic research, or simply indulging in the rich linguistic tapestry of Turkish, LexiTR provides the data-driven support you need to succeed.