1 |
Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
EAG: Extract and Generate Multi-way Aligned Corpus for Complete Multi-lingual Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Modeling Bilingual Conversational Characteristics for Neural Chat Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Sequence-Level Training for Non-Autoregressive Neural Machine Translation ...
|
|
|
|
Abstract:
In recent years, Neural Machine Translation (NMT) has achieved notable results in various translation tasks. However, the word-by-word generation manner determined by the autoregressive mechanism leads to high translation latency of the NMT and restricts its low-latency applications. Non-Autoregressive Neural Machine Translation (NAT) removes the autoregressive mechanism and achieves significant decoding speedup through generating target words independently and simultaneously. Nevertheless, NAT still takes the word-level cross-entropy loss as the training objective, which is not optimal because the output of NAT cannot be properly evaluated due to the multimodality problem. In this article, we propose using sequence-level training objectives to train NAT models, which evaluate the NAT outputs as a whole and correlates well with the real translation quality. Firstly, we propose training NAT models to optimize sequence-level evaluation metrics (e.g., BLEU) based on several novel reinforcement algorithms ... : Computational Linguistics Journal ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; I.2.7; Machine Learning cs.LG
|
|
URL: https://arxiv.org/abs/2106.08122 https://dx.doi.org/10.48550/arxiv.2106.08122
|
|
BASE
|
|
Hide details
|
|
10 |
Competence-based Curriculum Learning for Multilingual Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Towards Making the Most of Dialogue Characteristics for Neural Chat Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Prevent the Language Model from being Overconfident in Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Modeling Bilingual Conversational Characteristics for Neural Chat Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Selective Knowledge Distillation for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Target-oriented Fine-tuning for Zero-Resource Named Entity Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Exploring Dynamic Selection of Branch Expansion Orders for Code Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
The ICT ’s Patent MT System Description for NTCIR-9
|
|
|
|
In: http://research.nii.ac.jp/ntcir/workshop/OnlineProceedings9/NTCIR/19-NTCIR9-PATENTMT-XiongH.pdf
|
|
BASE
|
|
Show details
|
|
|
|