3 accepted papers
This paper addresses the efficiency challenge of Neural Architecture Search (NAS) by formulating the task as a ranking problem. Previous methods require numerous training examples to estimate the accurate performance of architectures, although the actual goal is to find the distinction between “good…
Traditional neural machine translation is limited to the topmost encoder layer’s context representation and cannot directly perceive the lower encoder layers. Existing solutions usually rely on the adjustment of network architecture, making the calculation more complicated or introducing additional…
Spoken language understanding (SLU), which mainly involves intent prediction and slot filling, is a core component of a spoken dialogue system. Usually, intent determination and slot filling are carried out independently. Recently, joint learning of intent determination and slot filling has been pro…