32,209 Hits in 4.5 sec

Measuring Immediate Adaptation Performance for Neural Machine Translation

Patrick Simianer, Joern Wuebker, John DeNero
2019 Proceedings of the 2019 Conference of the North  
To this end, we propose new metrics that directly evaluate immediate adaptation performance for machine translation.  ...  We use these metrics to choose the most suitable adaptation method from a range of different adaptation techniques for neural machine translation systems.  ...  and one-shot vocabulary acquisition as well as high corpus-level translation quality. 2 Measuring Immediate Adaptation Motivation For interactive, adaptive machine translation systems, perceived adaptation  ... 
doi:10.18653/v1/n19-1206 dblp:conf/naacl/SimianerWD19 fatcat:g5dx5lbkafh4rje72iyhndj64y

Non-Parametric Online Learning from Human Feedback for Neural Machine Translation [article]

Dongqi Wang, Haoran Wei, Zhirui Zhang, Shujian Huang, Jun Xie, Jiajun Chen
2021 arXiv   pre-print
translations are used to improve the neural machine translation (NMT) system.  ...  Experiments conducted on EMEA and JRC-Acquis benchmarks demonstrate that our proposed method obtains substantial improvements on translation accuracy and achieves better adaptation performance with less  ...  ing Immediate Adaptation Performance for Neural Machine Gu, J.; Wang, Y.; Cho, K.; and Li, V. O. 2018. Search engine Translation. In NAACL, 2038–2046. guided neural machine translation.  ... 
arXiv:2109.11136v3 fatcat:h4s5jgfcdvendjn4fptdzfqsb4

A Study on the Intelligent Translation Model for English Incorporating Neural Network Migration Learning

Yanbo Zhang, Xin Ning
2021 Wireless Communications and Mobile Computing  
problem of neural networks during training and to improve the generalization ability of end-to-end neural network machine translation models under low-resource conditions.  ...  on a supervised algorithm; then, for machine translation tasks with parallel corpus data resource-poor language machine translation tasks, migration learning techniques are used to prevent the overfitting  ...  of neural machine translation models.  ... 
doi:10.1155/2021/1244389 fatcat:zk7u6zm5dvcvraxtqa3bpxh4wy

A User-Study on Online Adaptation of Neural Machine Translation to Human Post-Edits [article]

Sariya Karimova, Patrick Simianer, Stefan Riezler (Heidelberg University)
2018 arXiv   pre-print
The advantages of neural machine translation (NMT) have been extensively validated for offline translation of several language pairs for different domains of spoken and written language.  ...  Our study involves 29 human subjects (translation students) whose post-editing effort and translation quality were measured on about 4,500 interactions of a human post-editor and a machine translation  ...  machine translation immediately after its inception.  ... 
arXiv:1712.04853v3 fatcat:igmcvmmvond5hdh5wezizw4r4m

The use of machine translation algorithm based on residual and LSTM neural network in translation teaching

Beibei Ren, Zhihan Lv
2020 PLoS ONE  
The feasibility of the model's performance, translation quality, and adaptability in practical teaching is analyzed to provide a theoretical basis for the research and application of the SCN-LSTM translation  ...  The results show that the capability of the neural network for translation teaching is nearly one times higher than that of the traditional N-tuple translation model, and the fusion model performs much  ...  Results and discussion Performance evaluation of machine translation model of neural network based on residual and LSTM Fig 10 shows the performance difference of different neural network machine translation  ... 
doi:10.1371/journal.pone.0240663 pmid:33211704 pmcid:PMC7676682 fatcat:wrzxb6ujircejd5o6pndi4yi2i

Continuous Adaptation to User Feedback for Statistical Machine Translation

Frédéric Blain, Fethi Bougares, Amir Hazem, Loïc Barrault, Holger Schwenk
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
This paper gives a detailed experiment feedback of different approaches to adapt a statistical machine translation system towards a targeted translation project, using only small amounts of parallel in-domain  ...  The experiments were performed by professional translators under realistic conditions of work using a computer assisted translation tool.  ...  Acknowledgments We thank the post-editors who took part to this experiment, as well as our anonymous reviewers for their feedback and suggestions.  ... 
doi:10.3115/v1/n15-1103 dblp:conf/naacl/BlainBHBS15 fatcat:kno5grwmenew5avg65zayusw7y

Deep Learning and the Global Workspace Theory [article]

Rufin VanRullen, Ryota Kanai
2021 arXiv   pre-print
We propose a roadmap based on unsupervised neural translation between multiple latent spaces (neural networks trained for distinct tasks, on distinct sensory inputs and/or modalities) to create a unique  ...  There is a growing need, however, for novel, brain-inspired cognitive architectures.  ...  We wish to thank Leila Reddy, Thomas Serre, Andrea Alamia, Milad Mozafari and Benjamin Devillers for helpful comments on the manuscript.  ... 
arXiv:2012.10390v2 fatcat:yeeqva4j4vhidlxrid34dytj4y

Application of Post-Edited Machine Translation in Fashion eCommerce

Kasia Kosmaczewska, Matt Train
2019 Machine Translation Summit  
key role in transitioning from human translation to statistical machine translation (SMT), and then from SMT to neural machine translation (NMT).  ...  Machine translation (MT) and post-edited machine translation (PEMT) have traditionally been explored primarily in the context of legal and medical content types, where MT results are often easier to predict  ...  As expected, in practice, the adaptive neural machine translation framework proved considerably more receptive to corrections made by post-editors, learning immediately from the post-edits, leading to  ... 
dblp:conf/mtsummit/KosmaczewskaT19 fatcat:aq4rwyeau5eklbpnkwosxsbqwi

Towards Domain Robustness of Neural Language Models

Michal Stefánik, Petr Sojka
2021 Recent Advances in Slavonic Natural Languages Processing  
generalization measures.  ...  This work summarises recent progress in generalization evaluation and training of deep neural networks, categorized in data-centric and model-centric overviews.  ...  Furthermore, our domains of interest might not even be preliminary known, as is often the native case in generative tasks, such as neural machine translation, summarization, or paraphrasing; think, for  ... 
dblp:conf/raslan/StefanikS21 fatcat:wwvovaesnffnflt627v22yydei

Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement [article]

Jason Lee, Elman Mansimov, Kyunghyun Cho
2018 arXiv   pre-print
We extensively evaluate the proposed model on machine translation (En-De and En-Ro) and image caption generation, and observe that it significantly speeds up decoding while maintaining the generation quality  ...  We propose a conditional non-autoregressive neural sequence model based on iterative refinement.  ...  We also thank Jiatao Gu for valuable feedback.  ... 
arXiv:1802.06901v3 fatcat:idmxzsinwvdplga7oiklfbfgrq

A Post-editing Interface for Immediate Adaptation in Statistical Machine Translation

Patrick Simianer, Sariya Karimova, Stefan Riezler
2016 International Conference on Computational Linguistics  
Adaptive machine translation (MT) systems are a promising approach for improving the effectiveness of computer-aided translation (CAT) environments.  ...  Our translation systems may learn from post-edits using several weight, language model and novel translation model adaptation techniques, in part by exploiting the output of the graphical interface.  ...  measures relevant for post-editing performance.  ... 
dblp:conf/coling/SimianerKR16 fatcat:wzev7m5ds5e7bkoyjmhmswrgf4

Human-Centered Design of Wearable Neuroprostheses and Exoskeletons

Jose L. Contreras-Vidal, Atilla Kilicarslan, He (Helen) Huang, Robert G. Grossman
2015 The AI Magazine  
We conclude with a summary of challenges to the translation of these complex human-machine systems to the end-user.  ...  Moreover, these complex human-machine systems should be effective, reliable, safe and engaging and support the patient in performing intended actions with minimal effort and errors with adequate interaction  ...  Other relevant metrics in exoskeleton systems augmented with brain-machine interfaces include quantification of (1) changes in patterns of brain activity (for example, EEG); (2) neural adaptation assessed  ... 
doi:10.1609/aimag.v36i4.2613 fatcat:xssgep6minbillpekvl4bed65q

Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement

Jason Lee, Elman Mansimov, Kyunghyun Cho
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
We extensively evaluate the proposed model on machine translation (En$De and En$Ro) and image caption generation, and observe that it significantly speeds up decoding while maintaining the generation quality  ...  We propose a conditional non-autoregressive neural sequence model based on iterative refinement.  ...  We also thank Jiatao Gu for valuable feedback.  ... 
doi:10.18653/v1/d18-1149 dblp:conf/emnlp/LeeMC18 fatcat:abgjrqls65h4zb5hfsyyap3hmy

Domain, Translationese and Noise in Synthetic Data for Neural Machine Translation [article]

Nikolay Bogoychev, Rico Sennrich
2020 arXiv   pre-print
The quality of neural machine translation can be improved by leveraging additional monolingual resources to create synthetic training data.  ...  We perform additional low-resource experiments which demonstrate that forward translation is more sensitive to the quality of the initial translation system than back-translation, and tends to perform  ...  Adapting neural machine translation with parallel synthetic data. In Proceedings of the Second Conference on Machine Translation, pages 138-147, Copenhagen, Denmark.  ... 
arXiv:1911.03362v2 fatcat:eyq4jun4p5cibkvuzojsvqdj5u

Neural translation and automated recognition of ICD10 medical entities from natural language [article]

Louis Falissard, Claire Morgand, Sylvie Roussel, Claire Imbaud, Walid Ghosn, Karim Bounebache, Grégoire Rey
2020 arXiv   pre-print
The recognition of medical entities from natural language is an ubiquitous problem in the medical field, with applications ranging from medical act coding to the analysis of electronic health data for  ...  This article investigates the applications of deep neural sequence models to the medical entity recognition from natural language problem.  ...  translation neural architecture, the Transformer.  ... 
arXiv:2004.13839v2 fatcat:v3ff7kwp7vdtdhsdxma66gp6qa
« Previous Showing results 1 — 15 out of 32,209 results