FormosanBank：人工智慧與計算分析的現狀、計劃及初步成果

摘要

　　Among under-resourced, endangered languages, the Formosan languages stand out as being particularly well-documented. This is in no small part due to the efforts of linguists at Academia Sinica and elsewhere in Taiwan. This strong foundation makes it possible to utilize additional tools from the language sciences: cognitive and neurolinguistic investigation, computational analysis, and of course artificial intelligence. The goal of FormosanBank -- now in its second year -- is to bring those tools to bear. In the first part of the talk, we describe progress on creating the free-and-open-access corpora that are at the heart of FormosanBank. Attendees with see demos and get a link to the published corpus. We will also present our initial results in machine translation, automatic speech recognition, and (if time permits) some initial computational analyses.