Year: 2016
Type: conference-paper
Abstract: We investigate how neural, encoder-decoder translation systems output target strings of appropriate lengths, finding that a collection of hidden units learns to explicitly implement this functionality.
DOI: 10.18653/v1/d16-1248
Authors: Xing Shi, Kevin Knight, Deniz Yuret
Institutions: University of Southern California, Koç University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2561386235