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 ...
|
|
|
|
Abstract:
Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces. Concerning the information aggregation, a common practice is to use a concatenation followed by a linear transformation, which may not fully exploit the expressiveness of multi-head attention. In this work, we propose to improve the information aggregation for multi-head attention with a more powerful routing-by-agreement algorithm. Specifically, the routing algorithm iteratively updates the proportion of how much a part (i.e. the distinct information learned from a specific subspace) should be assigned to a whole (i.e. the final output representation), based on the agreement between parts and wholes. Experimental results on linguistic probing tasks and machine translation tasks prove the superiority of the advanced information aggregation over the standard linear transformation. ... : NAACL 2019 ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1904.03100 https://dx.doi.org/10.48550/arxiv.1904.03100
|
|
BASE
|
|
Hide 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 ...
|
|
|
|
BASE
|
|
Show 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
|
|
|
|