DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5
Hits 1 – 20 of 93

1
Development and validation of the geriatrics health behavior questionnaire (GHBQ)
In: BMC Public Health (2022)
BASE
Show details
2
Enhanced protection face masks do not adversely impact thermophysiological comfort
In: PLoS One (2022)
BASE
Show details
3
Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help? ...
BASE
Show details
4
Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection ...
BASE
Show details
5
Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training ...
Wu, Minghao; Li, Yitong; Zhang, Meng. - : arXiv, 2021
BASE
Show details
6
Neural-Symbolic Commonsense Reasoner with Relation Predictors ...
BASE
Show details
7
Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection ...
BASE
Show details
8
Learning to Explain: Generating Stable Explanations Fast ...
BASE
Show details
9
It Is Not As Good As You Think! Evaluating Simultaneous Machine Translation on Interpretation Data ...
BASE
Show details
10
Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers ...
BASE
Show details
11
Cognition-aware Cognate Detection ...
BASE
Show details
12
Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection ...
Abstract: Anthology paper link: https://aclanthology.org/2021.emnlp-main.268/ Abstract: This paper considers the unsupervised domain adaptation problem for neural machine translation (NMT), where we assume the access to only monolingual text in either the source or target language in the new domain. We propose a cross-lingual data selection method to extract in-domain sentences in the missing language side from a large generic monolingual corpus. Our proposed method trains an adaptive layer on top of multilingual BERT by contrastive learning to align the representation between the source and target language. This then enables the transferability of the domain classifier between the languages in a zero-shot manner. Once the in-domain data is detected by the classifier, the NMT model is then adapted to the new domain by jointly learning translation and domain discrimination tasks. We evaluate our cross-lingual data selection method on NMT across five diverse domains in three language pairs, as well as a real-world ...
Keyword: Computational Linguistics; Covid-19; Language Models; Machine Learning; Machine Learning and Data Mining; Machine translation; Natural Language Processing
URL: https://dx.doi.org/10.48448/q8c1-ca75
https://underline.io/lecture/37992-generalised-unsupervised-domain-adaptation-of-neural-machine-translation-with-cross-lingual-data-selection
BASE
Hide details
13
Multilingual Neural Machine Translation: Can Linguistic Hierarchies Help? ...
BASE
Show details
14
Multilingual Simultaneous Neural Machine Translation ...
BASE
Show details
15
Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training ...
BASE
Show details
16
Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages ...
BASE
Show details
17
Two-Stage Recognition and beyond for Compound Facial Emotion Recognition
In: Electronics ; Volume 10 ; Issue 22 (2021)
BASE
Show details
18
Psychometric properties of modified MOS social support survey 5-item (MSSS-5-item) among Iranian older adults
In: BMC Geriatr (2021)
BASE
Show details
19
Concurrent Group-Dynamic Assessment of Intermediate EFL Learners’ Receptive and Productive Vocabulary Size
In: Porta Linguarum: revista internacional de didáctica de las lenguas extranjeras, ISSN 1697-7467, Nº. 36, 2021, pags. 119-137 (2021)
BASE
Show details
20
The Association of Experienced in-service EFL teachers’ immunity with engagement, emotions, and autonomy [<Journal>]
DNB Subject Category Language
Show details

Page: 1 2 3 4 5

Catalogues
0
0
3
0
4
0
0
Bibliographies
2
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
86
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern