一作NeurIPS 2026Poster
Computer Science Conferences Should Require Nonrepudiable Experimental Results
Mamadou K. Keita · Christopher M. Homan
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Mamadou K. Keita · Christopher M. Homan
Mamadou K. Keita · Christopher M. Homan · Huy Le
We introduce negative space learning machine translation (NSL-MT), a training method for underresourced languages, that augments limited parallel data with synthetically generated violations of the target language’s grammar and explicitly penalizes the model when it assigns high probability to th...