DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5
Hits 1 – 20 of 89

1
Universal Conditional Masked Language Pre-training for Neural Machine Translation ...
Li, Pengfei; Li, Liangyou; Zhang, Meng. - : arXiv, 2022
BASE
Show details
2
Compilable Neural Code Generation with Compiler Feedback ...
Wang, Xin; Wang, Yasheng; Wan, Yao. - : arXiv, 2022
BASE
Show details
3
Sub-Character Tokenization for Chinese Pretrained Language Models ...
BASE
Show details
4
Training Multilingual Pre-trained Language Model with Byte-level Subwords ...
Wei, Junqiu; Liu, Qun; Guo, Yinpeng. - : arXiv, 2021
BASE
Show details
5
Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021 ...
Zeng, Xingshan; Li, Liangyou; Liu, Qun. - : arXiv, 2021
BASE
Show details
6
JABER and SABER: Junior and Senior Arabic BERt ...
BASE
Show details
7
Learning Multilingual Representation for Natural Language Understanding with Enhanced Cross-Lingual Supervision ...
Guo, Yinpeng; Li, Liangyou; Jiang, Xin. - : arXiv, 2021
BASE
Show details
8
LightMBERT: A Simple Yet Effective Method for Multilingual BERT Distillation ...
BASE
Show details
9
Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training ...
Wu, Minghao; Li, Yitong; Zhang, Meng. - : arXiv, 2021
BASE
Show details
10
Improving Unsupervised Question Answering via Summarization-Informed Question Generation ...
BASE
Show details
11
CCA-MDD: A Coupled Cross-Attention based Framework for Streaming Mispronunciation detection and diagnosis ...
BASE
Show details
12
A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering ...
BASE
Show details
13
HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management ...
BASE
Show details
14
AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models ...
BASE
Show details
15
TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models ...
BASE
Show details
16
Two Parents, One Child: {D}ual Transfer for Low-Resource Neural Machine Translation ...
BASE
Show details
17
RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer ...
BASE
Show details
18
Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training ...
Abstract: Anthology paper link: https://aclanthology.org/2021.emnlp-main.580/ Abstract: Learning multilingual and multi-domain translation model is challenging as the heterogeneous and imbalanced data make the model converge inconsistently over different corpora in real world. One common practice is to adjust the share of each corpus in the training, so that the learning process is balanced and low-resource cases can benefit from the high resource ones. However, automatic balancing methods usually depend on the intra- and inter-dataset characteristics, which is usually agnostic or requires human priors. In this work, we propose an approach, MultiUAT, that dynamically adjusts the training data usage based on the model's uncertainty on a small set of trusted clean data for multi-corpus machine translation. We experiments with two classes of uncertainty measures on multilingual (16 languages with 4 settings) and multi-domain settings (4 for in-domain and 2 for out-of-domain on English-German translation) and demonstrate ...
Keyword: Computational Linguistics; Language Models; Machine Learning; Machine Learning and Data Mining; Machine translation; Natural Language Processing
URL: https://underline.io/lecture/37432-uncertainty-aware-balancing-for-multilingual
https://dx.doi.org/10.48448/gtwz-9008
BASE
Hide details
19
DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling ...
Wang, Baojun; Zhang, Zhao; Xu, Kun. - : arXiv, 2021
BASE
Show details
20
Document Graph for Neural Machine Translation ...
BASE
Show details

Page: 1 2 3 4 5

Catalogues
3
0
2
0
3
0
0
Bibliographies
3
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
79
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern