search

shunk031 / paper-survey

📚 Survey of previous research and related works on machine learning (especially Deep Learning) in Japanese
https://shunk031.github.io/paper-survey/
151 stars 12 forks source link

How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection #210

Closed shunk031 closed 5 years ago

shunk031 commented 5 years ago

https://arxiv.org/abs/1902.10339

shunk031 commented 5 years ago

精度を保ったまま最小限の語彙を選択する variational vocabulary dropout (VDD) を提案。多くのNLPタスクで用いる語彙数は昨今非常に大規模となるが、限られた計算リソース下での実行することは難しい。 そこでdropoutベースで精度低下に寄与しない単語を学習する枠組みを導入している。

How Large Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection - Paper Survey