1 |
Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Anatomical Study on the Safety of Anterior Cervical Craniovertebral Fusion with Clival Screw Placement in Children Aged 1–6 Years
|
|
|
|
In: Int J Gen Med (2021)
|
|
BASE
|
|
Show details
|
|
4 |
Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Assessing the Bilingual Knowledge Learned by Neural Machine Translation Models ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Information Aggregation for Multi-Head Attention with Routing-by-Agreement ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Neuron Interaction Based Representation Composition for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Multi-Granularity Self-Attention for Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Towards Understanding Neural Machine Translation with Word Importance ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Exploiting Deep Representations for Neural Machine Translation ...
|
|
|
|
Abstract:
Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures. However, only the top layers of encoder and decoder are leveraged in the subsequent process, which misses the opportunity to exploit the useful information embedded in other layers. In this work, we propose to simultaneously expose all of these signals with layer aggregation and multi-layer attention mechanisms. In addition, we introduce an auxiliary regularization term to encourage different layers to capture diverse information. Experimental results on widely-used WMT14 English-German and WMT17 Chinese-English translation data demonstrate the effectiveness and universality of the proposed approach. ... : EMNLP 2018 ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1810.10181 https://arxiv.org/abs/1810.10181
|
|
BASE
|
|
Hide details
|
|
13 |
Hardware string matching engine for large and dynamic pattern set ; Da xing dong tai zi fu chuan ji de ying jian pi pei ji ; 大型動態字符串集的硬件匹配機
|
|
Wang, Xing (王興). - : City University of Hong Kong, 2014
|
|
BASE
|
|
Show details
|
|
14 |
Multi-Stride String Searching for High-Speed Content Inspection
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Multi-Stride String Searching for High-Speed Content Inspection
|
|
|
|
BASE
|
|
Show details
|
|
|
|