scholarly journals Convolutional over Recurrent Encoder for Neural Machine Translation

2017 ◽  
Vol 108 (1) ◽  
pp. 37-48 ◽  
Author(s):  
Praveen Dakwale ◽  
Christof Monz
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Machine Translation ◽  
Recurrent Neural Network ◽  
Neural Machine Translation ◽  
German Translation ◽  
Source Sentence ◽  
End To End ◽  
Target Words

AbstractNeural machine translation is a recently proposed approach which has shown competitive results to traditional MT approaches. Standard neural MT is an end-to-end neural network where the source sentence is encoded by a recurrent neural network (RNN) called encoder and the target words are predicted using another RNN known as decoder. Recently, various models have been proposed which replace the RNN encoder with a convolutional neural network (CNN). In this paper, we propose to augment the standard RNN encoder in NMT with additional convolutional layers in order to capture wider context in the encoder output. Experiments on English to German translation demonstrate that our approach can achieve significant improvements over a standard RNN-based baseline.

scholarly journals ProLanGO: Protein Function Prediction Using Neural Machine Translation Based on a Recurrent Neural Network

Molecules ◽  
2017 ◽  
Vol 22 (10) ◽  
pp. 1732 ◽  
Author(s):  
Renzhi Cao ◽  
Colton Freitas ◽  
Leong Chan ◽  
Miao Sun ◽  
Haiqing Jiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Translation ◽  
Recurrent Neural Network ◽  
Protein Function ◽  
Protein Function Prediction ◽  
Function Prediction ◽  
Neural Machine Translation

Neural Machine Translation Using Sequence Modeling

2021 ◽  
Vol 9 (8) ◽  
pp. 2153-2169
Author(s):  
N Revathi
Keyword(s):  
Neural Network ◽  
Machine Translation ◽  
Language Processing ◽  
Recurrent Neural Network ◽  
Deep Neural Network ◽  
Short Term Memory ◽  
Short Term ◽  
Neural Machine Translation ◽  
Term Memory ◽  
Sequence Modeling

Abstract: Language is a main mode of communication, and translation is a critical tool for understanding information in a foreign language. Without the help of human translators, machine translation allows users to absorb unfamiliar linguistic material. The main goal of this project is to create a practical language translation from English to Hindi. Given its relevance and potential in the English-Hindi translation, machine translation is an efficient way to turn content into a new language without employing people. Among all available translation machines, Neural Machine Translation (NMT) is one of the most efficient ways. So, in this case, we're employing Sequence to Sequence Modeling, which includes the Recurrent Neural Network (RNN), Long and Short Term Memory (LSTM), and Encoder-Decoder methods. Deep Neural Network (DNN) comprehension and principles of deep learning, i.e. machine translation, are disclosed in the field of Natural Language Processing (NLP). In machine reclining techniques, DNN plays a crucial role. Keywords: Sequence to Sequence, Encoder-Decoder, Recurrent Neural Network, Long & Short term Memory, Deep Neural Network.

Research on Mongolian-Chinese machine translation based on the end-to-end neural network

2019 ◽  
Vol 18 (01) ◽  
pp. 1941003 ◽  
Author(s):  
Ren Qing-Dao-Er-Ji ◽  
Yila Su ◽  
Nier Wu
Keyword(s):  
Neural Network ◽  
Machine Translation ◽  
Language Processing ◽  
Conditional Random Field ◽  
Target Language ◽  
Word Alignment ◽  
Neural Machine Translation ◽  
Attention Model ◽  
End To End ◽  
Improved Model

With the development of natural language processing and neural machine translation, the neural machine translation method of end-to-end (E2E) neural network model has gradually become the focus of research because of its high translation accuracy and strong semantics of translation. However, there are still problems such as limited vocabulary and low translation loyalty, etc. In this paper, the discriminant method and the Conditional Random Field (CRF) model were used to segment and label the stem and affixes of Mongolian in the preprocessing stage of Mongolian-Chinese bilingual corpus. Aiming at the low translation loyalty problem, a decoding model combining Convolution Neural Network (CNN) and Gated Recurrent Unit (GRU) was constructed. The target language decoding was performed by using the GRU. A global attention model was used to obtain the bilingual word alignment information in the process of bilingual word alignment processing. Finally, the quality of the translation was evaluated by Bilingual Evaluation Understudy (BLEU) values and Perplexity (PPL) values. The improved model yields a BLEU value of 25.13 and a PPL value of [Formula: see text]. The experimental results show that the E2E Mongolian-Chinese neural machine translation model was improved in terms of translation quality and semantic confusion compared with traditional statistical methods and machine translation models based on Recurrent Neural Networks (RNN).

scholarly journals ME-MD: An Effective Framework for Neural Machine Translation with Multiple Encoders and Decoders

2017 ◽  
Author(s):  
Jinchao Zhang ◽  
Qun Liu ◽  
Jie Zhou
Keyword(s):  
Machine Translation ◽  
English Translation ◽  
State Of The Art ◽  
The State ◽  
Neural Machine Translation ◽  
Source Sentence ◽  
Target Words

The encoder-decoder neural framework is widely employed for Neural Machine Translation (NMT) with a single encoder to represent the source sentence and a single decoder to generate target words. The translation performance heavily relies on the representation ability of the encoder and the generation ability of the decoder. To further enhance NMT, we propose to extend the original encoder-decoder framework to a novel one, which has multiple encoders and decoders (ME-MD). Through this way, multiple encoders extract more diverse features to represent the source sequence and multiple decoders capture more complicated translation knowledge. Our proposed ME-MD framework is convenient to integrate heterogeneous encoders and decoders with multiple depths and multiple types. Experiment on Chinese-English translation task shows that our ME-MD system surpasses the state-of-the-art NMT system by 2.1 BLEU points and surpasses the phrase-based Moses by 7.38 BLEU points. Our framework is general and can be applied to other sequence to sequence tasks.

scholarly journals Neural Machine Translation using Recurrent Neural Network

2020 ◽  
Vol 9 (4) ◽  
pp. 1395-1400
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Machine Translation ◽  
Recurrent Neural Network ◽  
Machine Learning Algorithms ◽  
The Other ◽  
Neural Machine Translation ◽  
To Come ◽  
Artificial Neural Network Ann ◽  
Translation Systems

In this era of globalization, it is quite likely to come across people or community who do not share the same language for communication as us. To acknowledge the problems caused by this, we have machine translation systems being developed. Developers of several reputed organizations like Google LLC, have been working to bring algorithms to support machine translations using machine learning algorithms like Artificial Neural Network (ANN) in order to facilitate machine translation. Several Neural Machine Translations have been developed in this regard, but Recurrent Neural Network (RNN), on the other hand, has not grown much in this field. In our work, we have tried to bring RNN in the field of machine translations, in order to acknowledge the benefits of RNN over ANN. The results show how RNN is able to perform machine translations with proper accuracy.

scholarly journals Analisis Perbandingan Nilai Akurasi Mekanisme Attention Bahdanau dan Luong pada Neural Machine Translation Bahasa Indonesia ke Bahasa Melayu Ketapang dengan Arsitektur Recurrent Neural Network

2021 ◽  
Vol 7 (3) ◽  
pp. 488
Author(s):  
Wahyu Gunawan ◽  
Herry Sujaini ◽  
Tursina Tursina
Keyword(s):  
Neural Network ◽  
Machine Translation ◽  
Recurrent Neural Network ◽  
Cross Validation ◽  
Neural Machine Translation ◽  
Fold Cross Validation ◽  
Bahasa Indonesia

Di Indonesia, penerapan mesin penerjemah masih banyak dilakukan dengan berbasis statistik khususnya dalam eksperimen penerjemahan bahasa daerah. Dalam beberapa tahun terakhir, mesin penerjemah jaringan saraf tiruan telah mencapai kesuksesan yang luar biasa dan menjadi metode pilihan baru dalam praktik mesin penerjemah. pada penelitian ini menggunakan mekanisme attention dari Bahdanau dan Luong dalam bahasa Indonesia ke bahasa Melayu Ketapang dengan data korpus paralel sejumlah 5000 baris kalimat. Hasil pengujian berdasarkan metode penambahan secara konsisten dengan jumlah epoch didapatkan nilai skor BLEU yaitu pada attention Bahdanau menghasilkan akurasi 35,96% tanpa out-of-vocabulary (OOV) dengan menggunakan jumlah epoch 40, sedangkan pada attention Luong menghasilkan akurasi 26,19% tanpa OOV menggunakan jumlah 30 epoch. Hasil pengujian berdasarkan k-fold cross validation didapatkan nilai rata-rata akurasi tertinggi sebesar 40,25% tanpa OOV untuk attention Bahdanau dan 30,38% tanpa OOV untuk attention Luong, sedangkan pengujian manual oleh dua orang ahli bahasa memperoleh nilai akurasi sebesar 78,17% dan 72,53%. 

scholarly journals Matching Large Baseline Oblique Stereo Images Using an End-to-End Convolutional Neural Network

2021 ◽  
Vol 13 (2) ◽  
pp. 274
Author(s):  
Guobiao Yao ◽  
Alper Yilmaz ◽  
Li Zhang ◽  
Fei Meng ◽  
Haibin Ai ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Stereo Matching ◽  
Least Square ◽  
Affine Invariant ◽  
Stereo Images ◽  
Distance Ratio ◽  
Matching Algorithm ◽  
End To End

The available stereo matching algorithms produce large number of false positive matches or only produce a few true-positives across oblique stereo images with large baseline. This undesired result happens due to the complex perspective deformation and radiometric distortion across the images. To address this problem, we propose a novel affine invariant feature matching algorithm with subpixel accuracy based on an end-to-end convolutional neural network (CNN). In our method, we adopt and modify a Hessian affine network, which we refer to as IHesAffNet, to obtain affine invariant Hessian regions using deep learning framework. To improve the correlation between corresponding features, we introduce an empirical weighted loss function (EWLF) based on the negative samples using K nearest neighbors, and then generate deep learning-based descriptors with high discrimination that is realized with our multiple hard network structure (MTHardNets). Following this step, the conjugate features are produced by using the Euclidean distance ratio as the matching metric, and the accuracy of matches are optimized through the deep learning transform based least square matching (DLT-LSM). Finally, experiments on Large baseline oblique stereo images acquired by ground close-range and unmanned aerial vehicle (UAV) verify the effectiveness of the proposed approach, and comprehensive comparisons demonstrate that our matching algorithm outperforms the state-of-art methods in terms of accuracy, distribution and correct ratio. The main contributions of this article are: (i) our proposed MTHardNets can generate high quality descriptors; and (ii) the IHesAffNet can produce substantial affine invariant corresponding features with reliable transform parameters.

scholarly journals A Review of Plant Phenotypic Image Recognition Technology Based on Deep Learning

Electronics ◽  
2021 ◽  
Vol 10 (1) ◽  
pp. 81
Author(s):  
Jianbin Xiong ◽  
Dezheng Yu ◽  
Shuangyin Liu ◽  
Lei Shu ◽  
Xiaochan Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Plant Species ◽  
Image Recognition ◽  
Recurrent Neural Network ◽  
Plant Diseases ◽  
Learning Methods ◽  
Smart Agriculture ◽  
Important Branch

Plant phenotypic image recognition (PPIR) is an important branch of smart agriculture. In recent years, deep learning has achieved significant breakthroughs in image recognition. Consequently, PPIR technology that is based on deep learning is becoming increasingly popular. First, this paper introduces the development and application of PPIR technology, followed by its classification and analysis. Second, it presents the theory of four types of deep learning methods and their applications in PPIR. These methods include the convolutional neural network, deep belief network, recurrent neural network, and stacked autoencoder, and they are applied to identify plant species, diagnose plant diseases, etc. Finally, the difficulties and challenges of deep learning in PPIR are discussed.

Sign in / Sign up

Export Citation Format

Share Document