Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search
Gyuwan Kim, Kyunghyun Cho
Abstract
Gyuwan Kim, Kyunghyun Cho. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.
Topics & Concepts
Computer scienceTransformerDrop (telecommunication)Natural language processingSpeech recognitionEngineeringElectrical engineeringTelecommunicationsVoltageTopic ModelingNatural Language Processing TechniquesMultimodal Machine Learning Applications