z-logo
open-access-imgOpen Access
A Continuous Relaxation of Beam Search for End-to-End Training of Neural Sequence Models
Author(s) -
Kartik Goyal,
Graham Neubig,
Chris Dyer,
Taylor Berg-Kirkpatrick
Publication year - 2018
Publication title -
proceedings of the aaai conference on artificial intelligence
Language(s) - English
Resource type - Journals
eISSN - 2374-3468
pISSN - 2159-5399
DOI - 10.1609/aaai.v32i1.11806
Subject(s) - beam search , decoding methods , computer science , greedy algorithm , cross entropy , entropy (arrow of time) , algorithm , list decoding , search algorithm , metric (unit) , sequence (biology) , artificial intelligence , principle of maximum entropy , concatenated error correction code , engineering , block code , operations management , physics , quantum mechanics , biology , genetics

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here
Accelerating Research

Address

John Eccles House
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom