Regularizing Neural Networks by Penalizing Confident Output Distributions

arXiv (Cornell University)

DOI: 10.48550/arxiv.1701.06548 Full text (OA) OpenAlex

Authors 0

Author list not loaded yet.

Cited by 6 stored of 360

Tight Integrated End-to-End Training for Cascaded Speech Translation
2021 IEEE Spoken Language Technology Workshop (SLT) conference-paper Computer Science Speech Recognition and Synthesis Open access cited by 1 patent

30

citations
Without Further Ado: Direct and Simultaneous Speech Translation by AppTek in 2021
2021 International Conference on Spoken Language Translation (IWSLT) conference-paper Computer Science Speech Recognition and Synthesis Open access

7

citations
Start-Before-End and End-to-End: Neural Speech Translation by AppTek and RWTH Aachen University
2020 International Conference on Spoken Language Translation (IWSLT) conference-paper Computer Science Speech Recognition and Synthesis Open access

17

citations
Towards a Better Understanding of Label Smoothing in Neural Machine Translation
2020 Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing (AACL-IJCNLP) conference-paper Computer Science Natural Language Processing Techniques Open access

16

citations
Multi-Agent Mutual Learning at Sentence-Level and Token-Level for Neural Machine Translation
2020 conference-paper Computer Science Natural Language Processing Techniques Open access

5

citations
Unifying Input and Output Smoothing in Neural Machine Translation
2020 International Conference on Computational Linguistics conference-paper Computer Science Natural Language Processing Techniques Open access

3

citations

6 results

Regularizing Neural Networks by Penalizing Confident Output Distributions

Authors 0

Cited by 6 stored of 360

References 0