Towards a General-Purpose Linguistic Annotation Backend

• DOI: 10.33011/computel.v2i.437
• Publication Date: 2021-03-22T20:38:37Z
• Authors: Graham Neubig; Patrick Littell; Chian-Yu Chen; Jean Lee; Zirui Li; Yu-Hsiang Lin; Yuyan Zhang
• Keywords: Upload; Transcription

Language documentation is inherently a time-intensive process; transcription, glossing, and corpus management consume significant portion of documentary linguists’ work. Advances in natural language processing can help to accelerate this work, using the past decisions as training material, but questions remain about how prioritize human involvement. In extended abstract, we describe beginnings new project that will attempt ease process through use (NLP) technology. It based on (1) methods adapt NLP tools languages, recent advances massively multilingual neural networks, (2) backend APIs interfaces allow linguists upload their data (§2). We then our current progress two fronts: automatic phoneme glossing (§3). Finally, briefly future directions (§4).