1 |
Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Edinburgh’s End-to-End Multilingual Speech Translation System for IWSLT 2021 ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
On Sparsifying Encoder Outputs in Sequence-to-Sequence Models ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Beyond Sentence-Level End-to-End Speech Translation: Context Helps ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Exploring Dynamic Selection of Branch Expansion Orders for Code Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual Translation
|
|
|
|
In: Zhang, Biao; Bapna, Ankur; Sennrich, Rico; Firat, Orhan (2021). Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual Translation. In: International Conference on Learning Representations, Virtual, 3 May 2021 - 7 May 2021, ICLR. (2021)
|
|
BASE
|
|
Show details
|
|
8 |
ParBLEU: Augmenting Metrics with Automatic Paraphrases for the WMT'20 Metrics Shared Task
|
|
|
|
In: Proceedings of the 5th Conference on Machine Translation ; 5th Conference on Machine Translation ; https://hal.archives-ouvertes.fr/hal-02981143 ; 5th Conference on Machine Translation, Nov 2020, Online, Unknown Region (2020)
|
|
Abstract:
International audience ; We describe parBLEU, parCHRF++, and parESIM, which augment baseline metrics with automatically generated paraphrases produced by PRISM (Thompson and Post, 2020a), a multilingual neural machine translation system. We build on recent work studying how to improve BLEU by using diverse automatically paraphrased references (Bawden et al., 2020), extending experiments to the multilingual setting for the WMT2020 metrics shared task and for three base metrics. We compare their capacity to exploit up to 100 additional synthetic references. We find that gains are possible when using additional, automatically paraphrased references, although they are not systematic. However, segment-level correlations, particularly into English, are improved for all three metrics and even with higher numbers of paraphrased references.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; evaluation; machine translation; metrics; paraphrasing
|
|
URL: https://hal.archives-ouvertes.fr/hal-02981143/file/Parbleu_system_paper-10.pdf https://hal.archives-ouvertes.fr/hal-02981143 https://hal.archives-ouvertes.fr/hal-02981143/document
|
|
BASE
|
|
Hide details
|
|
9 |
Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Adaptive Feature Selection for End-to-End Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Brain Structural and Functional Alterations Specific to Low Sleep Efficiency in Major Depressive Disorder
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Revisiting Low-Resource Neural Machine Translation: A Case Study ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|