Peran Text Processing Dalam Aplikasi Penerjemah Multi Bahasa Menggunakan Ajax API Google

Mesin penerjemah adalah alat penerjemah otomatis pada sebuah teks yang dapat merubah dari satu bahasa ke bahasa yang berbeda. Mesin penerjemah adalah sebuah software dengan hasil terjemahan dihasilkan atas dasar model linier regresi yang parameter-parameternya diambil dari hasil analisis statistik teks bilingual. Sekarang kami memperkenalkan langkah berikutnya dalam membuat Mesin Penerjemah yang lebih baik menggunakan metode Neural Machine Translation.Cara Neural Machine Translation menerjemahkan seluruh kalimat dalam satu waktu, bukan hanya memenggal sepotong demi sepotong. Menggunakan konteks yang lebih luas untuk membantu mencari tahu terjemahan yang paling relevan, yang kemudian menata kembali dan menyesuaikan untuk menjadi lebih seperti layaknya berbicara dengan manusia menggunakan tata bahasa yang benar.Program aplikasi ini dibuat menggunakan Bahasa pemrograman C# ditambah pustaka AJAX API Google untuk menerjemahkan teks dan mengambil terjemahan dengan mengurai konten JSON.Dari hasil penelitian didapat sebuah terjemahan yang jauh lebih halus dan mudah dibaca, dan ini semua mungkin karena sistem pembelajaran end-to-end yang dibangun di atas Neural Machine Translation yang pada dasarnya berarti bahwa sistem belajar dari waktu ke waktu untuk membuat lebih baik, terjemahan yang lebih alami.

Investigating usability in postediting neural machine translation: Evidence from translation trainees' self-perception and performance

Across Languages and Cultures ◽

10.1556/084.2021.00006 ◽

2021 ◽

Vol 22 (1) ◽

pp. 100-123

Author(s):

Xiangling Wang ◽

Tingting Wang ◽

Ricardo Muñoz Martín ◽

Yanfang Jia

Keyword(s):

Machine Translation ◽

Processing Speed ◽

Text Processing ◽

Ease Of Use ◽

Chinese Translation ◽

Translation Quality ◽

Retrospective Reports ◽

And Performance ◽

Translation Systems

AbstractThis is a report on an empirical study on the usability for translation trainees of neural machine translation systems when post-editing (mtpe). Sixty Chinese translation trainees completed a questionnaire on their perceptions of mtpe's usability. Fifty of them later performed both a post-editing task and a regular translation task, designed to examine mtpe's usability by comparing their performance in terms of text processing speed, effort, and translation quality. Contrasting data collected by the questionnaire, keylogging, eyetracking and retrospective reports we found that, compared with regular, unaided translation, mtpe's usefulness in performance was remarkable: (1) it increased translation trainees' text processing speed and also improved their translation quality; (2) mtpe's ease of use in performance was partly proved in that it significantly reduced informants' effort as measured by (a) fixation duration and fixation counts; (b) total task time; and (c) the number of insertion keystrokes and total keystrokes. However, (3) translation trainees generally perceived mtpe to be useful to increase productivity, but they were skeptical about its use to improve quality. They were neutral towards the ease of use of mtpe.

End-to-end entity-aware neural machine translation

Machine Learning ◽

10.1007/s10994-021-06073-9 ◽

2022 ◽

Author(s):

Shufang Xie ◽

Yingce Xia ◽

Lijun Wu ◽

Yiqing Huang ◽

Yang Fan ◽

...

Keyword(s):

Machine Translation ◽

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

International Journal of Wavelets Multiresolution and Information Processing ◽

10.1142/s0219691319410030 ◽

2019 ◽

Vol 18 (01) ◽

pp. 1941003 ◽

Cited By ~ 1

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 ◽

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).

End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification

10.18653/v1/d18-1336 ◽

2018 ◽

Cited By ~ 2

Author(s):

Jindřich Libovický ◽

Jindřich Helcl

Keyword(s):

Machine Translation ◽

Connectionist Temporal Classification

End To End ◽

Multi-Head Attention for End-to-End Neural Machine Translation

2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP) ◽

10.1109/iscslp.2018.8706667 ◽

2018 ◽

Author(s):

Ivan Fung ◽

Brian Mak

Keyword(s):

Machine Translation ◽

Towards End-to-End In-Image Neural Machine Translation

10.18653/v1/2020.nlpbt-1.8 ◽

2020 ◽

Author(s):

Elman Mansimov ◽

Mitchell Stern ◽

Mia Chen ◽

Orhan Firat ◽

Jakob Uszkoreit ◽

...

Keyword(s):

Machine Translation ◽

Convolutional over Recurrent Encoder for Neural Machine Translation

Prague Bulletin of Mathematical Linguistics ◽

10.1515/pralin-2017-0007 ◽

2017 ◽

Vol 108 (1) ◽

pp. 37-48 ◽

Cited By ~ 2

Author(s):

Praveen Dakwale ◽

Christof Monz

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Machine Translation ◽

Recurrent Neural Network ◽

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.