主催: The Japanese Society for Artificial Intelligence
会議名: 2021年度人工知能学会全国大会(第35回)
回次: 35
開催地: オンライン
開催日: 2021/06/08 - 2021/06/11
Distributed word representation greatly promoted research in NLP. Same as languages, MIDI music is constructed in the way of sequence, with a determined alphabet of notes and events. We proposed a way of training MIDI note embedding with an adaption of Facebook's fastText model. We then evaluate the model by word similarity, word analogy, and a classification task. The result shows that the adopted fastText model generalizes well in MIDI data and it’s promising to be used on future downstream tasks.