A research-grade platform for Khmer corpus linguistics.
Explore the built-in កម្ពុជសុរិយា (Kambuja Suriya) sample archive — eighty years of Cambodia's oldest scholarly journal, word-segmented and indexed for frequency, concordance, collocation, keyness, dispersion and part-of-speech analysis. On the Pro plan, upload your own Khmer text or PDF (scanned pages included) and get the same analysis on your own corpus.
Sample archive at a glance
Everything a corpus linguist needs
Frequency and lexical-richness statistics, KWIC concordancing, collocation and co-occurrence networks, keyness, dispersion, POS tagging, named-entity recognition, and more — grouped into a clean, dropdown-organised workbench.
Frequency & lexical richness
Ranked word lists, TTR/STTR/MATTR, Herdan's C, Guiraud's R.
Concordance (KWIC)
Every occurrence of a word in context, sortable by left/right/POS.
Collocations & networks
MI, t-score, log-likelihood, Dice — plus a visual "mental lexicon" graph.
Keyness
What's distinctive about one journal year versus the rest of the archive.
POS & named entities
A trained HMM tagger (~89% accuracy) and gazetteer NER for people, places, villages.
Segmentation, IPA, X-bar
Word-segment raw Khmer text, transcribe to IPA, and visualise syntax trees.
Simple pricing
The full analysis toolkit is free for everyone. Researcher adds unlimited export and creating your own corpus from uploaded text; Pro adds building a corpus straight from the web.
- Full analysis toolkit — frequency, concordance, collocations, keyness, POS, NER, dispersion, segmentation, IPA, X-bar
- View and work with the existing corpus
- No downloads
- Can't create a new corpus
- Everything in Free
- ⬇ Unlimited CSV, text & PNG export
- Create your own corpus — paste Khmer text, or upload PDFs and .txt files
- Every analysis tool runs on your own corpus too
- Everything in Researcher
- 🕸 Web crawling — paste Khmer website links and we fetch, clean, segment and index the text as your own corpus
- Priority support