Resources for Turkish

Morphological analysis

Free software

• TRMorph "is a relatively complete morphological analyzer for Turkish. It is implemented using SFST, and uses a lexicon based on (but heavily modified) the wordlist of Zemberek spell checker. The morphological analyzer is distributed under the GPL."

Lexical resources

• Turkish Language Association

Corpora

Free

• Southeast European Times (sentence aligned corpus, Albanian, Bulgarian, English, Greek, Macedonian, Romanian, Serbo-Croatian, Turkish — approximately 4.5 million words per language)

Proprietary

• HamleDT, harmonized dependency treebanks of many languages, common annotation style.
• TS Corpus (PoSTagged Turkish Corpus. The corpus also presents morphological and lemma tags of the data. Consists of 491 Million tokens)
• METU-Sabanci Turkish treebank
• Turkish plain text and Co-occurrences at LCC

Bibliography

• K. Oflazer, "Two-level Description of Turkish Morphology," Literary and Linguistic Computing, vol. 9, pp. 137-148, 1995. Backwards PDF

External links

• Sabancı University Natural Language Processing Tools (Turkish Morphological Analyzer, BalkaNET)
• Istanbul Technical University Natural Language Processing Research Group
• NooJ_TR by Mersin University Turkish National Corpus Project Team