Field linguists, students, and documentation teams
Language documentation and analysis pipeline
Start with preparing questionnaires then deploy this on Atekho for field data collection. Atekho allows for both field and follow-up remote data collection workflows. Atekho data is automatically synced to the cloud database for validation and further processing. Once data is validated and accepted, sentential and narrative data can be processed in MATra Lab with AI-assisted transcription, translation, and glossing. This could be used for analysing grammatical structures or writing grammatical descriptions of the language. Lexical data can be processed in LexiLab to produce multimodal, multilingual dictionaries. Finally, all outputs can be packaged for delivery to archives, for printing (especially dictionaries) or other downstream applications.