1 |
Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Efficient Test Time Adapter Ensembling for Low-resource Language Varieties ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Modeling Disclosive Transparency in NLP Application Descriptions ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Efficient Test Time Adapter Ensembling for Low-resource Language Varieties ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Balancing Training for Multilingual Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Multilingual Neural Machine Translation With Soft Decoupled Encoding ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
A Tree-based Decoder for Neural Machine Translation ...
|
|
|
|
Abstract:
Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes some specific types of linguistically-inspired tree structures, like constituency and dependency parse trees. This is often done via a standard RNN decoder that operates on a linearized target tree structure. However, it is an open question of what specific linguistic formalism, if any, is the best structural representation for NMT. In this paper, we (1) propose an NMT model that can naturally generate the topology of an arbitrary tree structure on the target side, and (2) experiment with various target tree structures. Our experiments show the surprising result that our model delivers the best improvements with balanced binary trees constructed without any linguistic knowledge; this model outperforms standard seq2seq models by up to 2.1 BLEU points, and other methods for incorporating target-side syntax by up to 0.7 BLEU. ... : Accepted as a short paper at the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018) ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1808.09374 https://arxiv.org/abs/1808.09374
|
|
BASE
|
|
Hide details
|
|
13 |
Influence of Ideological Manipulation on Slogan Translation - A Comparative Study on Two Chinese Versions of George Orwell's novel Nineteen Eighty-Four
|
|
Wang, Xinyi. - : The University of Queensland, School of Languages and Cultures, 2018
|
|
BASE
|
|
Show details
|
|
15 |
Generic decision-making on the retreatment of copper tailings dams
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Generic decision-making on the retreatment of copper tailings dams
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Generic decision-making on the retreatment of copper tailings dams ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Generic decision-making on the retreatment of copper tailings dams
|
|
|
|
BASE
|
|
Show details
|
|
|
|