scholarly journals Controlling Neural Machine Translation Formality with Synthetic Supervision

2020 ◽  
Vol 34 (05) ◽  
pp. 8568-8575
Author(s):  
Xing Niu ◽  
Marine Carpuat
Keyword(s):  
Machine Translation ◽  
Target Language ◽  
Sentence Pair ◽  
English Sentence ◽  
Neural Machine Translation ◽  
Source Language ◽  
Training Scheme ◽  
Training Examples ◽  
Language Content ◽  
Missing Element

This work aims to produce translations that convey source language content at a formality level that is appropriate for a particular audience. Framing this problem as a neural sequence-to-sequence task ideally requires training triplets consisting of a bilingual sentence pair labeled with target language formality. However, in practice, available training examples are limited to English sentence pairs of different styles, and bilingual parallel sentences of unknown formality. We introduce a novel training scheme for multi-task models that automatically generates synthetic training triplets by inferring the missing element on the fly, thus enabling end-to-end training. Comprehensive automatic and human assessments show that our best model outperforms existing models by producing translations that better match desired formality levels while preserving the source meaning.1

scholarly journals A Study of Neural Machine Translation from Chinese to Urdu

2020 ◽  
Vol 2 (4) ◽  
pp. 28
Author(s):  
. Zeeshan
Keyword(s):  
Machine Translation ◽  
Chinese Language ◽  
Language Translation ◽  
Target Language ◽  
Foreign Languages ◽  
Neural Machine Translation ◽  
Source Language ◽  
Great Progress ◽  
Score Method ◽  
Translation Methods

Machine Translation (MT) is used for giving a translation from a source language to a target language. Machine translation simply translates text or speech from one language to another language, but this process is not sufficient to give the perfect translation of a text due to the requirement of identification of whole expressions and their direct counterparts. Neural Machine Translation (NMT) is one of the most standard machine translation methods, which has made great progress in the recent years especially in non-universal languages. However, local language translation software for other foreign languages is limited and needs improving. In this paper, the Chinese language is translated to the Urdu language with the help of Open Neural Machine Translation (OpenNMT) in Deep Learning. Firstly, a Chineseto Urdu language sentences datasets were established and supported with Seven million sentences. After that, these datasets were trained by using the Open Neural Machine Translation (OpenNMT) method. At the final stage, the translation was compared to the desired translation with the help of the Bleu Score Method.

scholarly journals Knowledge Graphs Effectiveness in Neural Machine Translation Improvement

2020 ◽  
Vol 21 (3) ◽  
Author(s):  
Benyamin Ahmadnia ◽  
Bonnie J. Dorr ◽  
Parisa Kordjamshidi
Keyword(s):  
Machine Translation ◽  
Semantic Representation ◽  
Language Translation ◽  
Semantic Relations ◽  
Training Data ◽  
Target Language ◽  
Neural Machine Translation ◽  
Source Language ◽  
Knowledge Graphs ◽  
Unknown Words

Neural Machine Translation (NMT) systems require a massive amount of Maintaining semantic relations between words during the translation process yields more accurate target-language output from Neural Machine Translation (NMT). Although difficult to achieve from training data alone, it is possible to leverage Knowledge Graphs (KGs) to retain source-language semantic relations in the corresponding target-language translation. The core idea is to use KG entity relations as embedding constraints to improve the mapping from source to target. This paper describes two embedding constraints, both of which employ Entity Linking (EL)---assigning a unique identity to entities---to associate words in training sentences with those in the KG: (1) a monolingual embedding constraint that supports an enhanced semantic representation of the source words through access to relations between entities in a KG; and (2) a bilingual embedding constraint that forces entity relations in the source-language to be carried over to the corresponding entities in the target-language translation. The method is evaluated for English-Spanish translation exploiting Freebase as a source of knowledge. Our experimental results show that exploiting KG information not only decreases the number of unknown words in the translation but also improves translation quality.

scholarly journals Unraveling the Contribution of Image Captioning and Neural Machine Translation for Multimodal Machine Translation

2017 ◽  
Vol 108 (1) ◽  
pp. 197-208 ◽  
Author(s):  
Chiraag Lala ◽  
Pranava Madhyastha ◽  
Josiah Wang ◽  
Lucia Specia
Keyword(s):  
Recent Work ◽  
Machine Translation ◽  
Visual Information ◽  
Target Language ◽  
Image Captioning ◽  
Neural Machine Translation ◽  
Source Language ◽  
Translation Quality ◽  
Depth Study ◽  
Image Descriptions

AbstractRecent work on multimodal machine translation has attempted to address the problem of producing target language image descriptions based on both the source language description and the corresponding image. However, existing work has not been conclusive on the contribution of visual information. This paper presents an in-depth study of the problem by examining the differences and complementarities of two related but distinct approaches to this task: textonly neural machine translation and image captioning. We analyse the scope for improvement and the effect of different data and settings to build models for these tasks. We also propose ways of combining these two approaches for improved translation quality.

scholarly journals Optimizing Tokenization Choice for Machine Translation across Multiple Target Languages

2017 ◽  
Vol 108 (1) ◽  
pp. 257-269 ◽  
Author(s):  
Nasser Zalmout ◽  
Nizar Habash
Keyword(s):  
Machine Translation ◽  
Performance Enhancement ◽  
Statistical Machine Translation ◽  
Target Language ◽  
Source Language ◽  
Context Variable ◽  
Significant Performance ◽  
Morphologically Rich Languages ◽  
Target Languages ◽  
Language Text

AbstractTokenization is very helpful for Statistical Machine Translation (SMT), especially when translating from morphologically rich languages. Typically, a single tokenization scheme is applied to the entire source-language text and regardless of the target language. In this paper, we evaluate the hypothesis that SMT performance may benefit from different tokenization schemes for different words within the same text, and also for different target languages. We apply this approach to Arabic as a source language, with five target languages of varying morphological complexity: English, French, Spanish, Russian and Chinese. Our results show that different target languages indeed require different source-language schemes; and a context-variable tokenization scheme can outperform a context-constant scheme with a statistically significant performance enhancement of about 1.4 BLEU points.

scholarly journals IntroVNMT: An Introspective Model for Variational Neural Machine Translation

2020 ◽  
Vol 34 (05) ◽  
pp. 8830-8837
Author(s):  
Xin Sheng ◽  
Linli Xu ◽  
Junliang Guo ◽  
Jingchang Liu ◽  
Ruoyu Zhao ◽  
...  
Keyword(s):  
Machine Translation ◽  
Latent Variables ◽  
Image Synthesis ◽  
Target Language ◽  
Generative Adversarial Network ◽  
Neural Machine Translation ◽  
Adversarial Network ◽  
Proposed Model ◽  
Model Training ◽  
High Level

We propose a novel introspective model for variational neural machine translation (IntroVNMT) in this paper, inspired by the recent successful application of introspective variational autoencoder (IntroVAE) in high quality image synthesis. Different from the vanilla variational NMT model, IntroVNMT is capable of improving itself introspectively by evaluating the quality of the generated target sentences according to the high-level latent variables of the real and generated target sentences. As a consequence of introspective training, the proposed model is able to discriminate between the generated and real sentences of the target language via the latent variables generated by the encoder of the model. In this way, IntroVNMT is able to generate more realistic target sentences in practice. In the meantime, IntroVNMT inherits the advantages of the variational autoencoders (VAEs), and the model training process is more stable than the generative adversarial network (GAN) based models. Experimental results on different translation tasks demonstrate that the proposed model can achieve significant improvements over the vanilla variational NMT model.

Deep Learning-based Roman-Urdu to Urdu Transliteration

2020 ◽  
pp. 2152001
Author(s):  
Mehreen Alam ◽  
Sibt ul Hussain
Keyword(s):  
Machine Translation ◽  
State Of The Art ◽  
Research Problem ◽  
Attention Mechanism ◽  
Data Driven ◽  
Neural Machine Translation ◽  
Parallel Corpus ◽  
Source Language ◽  
Data Driven Approach ◽  
Modern Machine

Attention-based encoder-decoder models have superseded conventional techniques due to their unmatched performance on many neural machine translation problems. Usually, the encoders and decoders are two recurrent neural networks where the decoder is directed to focus on relevant parts of the source language using attention mechanism. This data-driven approach leads to generic and scalable solutions with no reliance on manual hand-crafted features. To the best of our knowledge, none of the modern machine translation approaches has been applied to address the research problem of Urdu machine transliteration. Ours is the first attempt to apply the deep neural network-based encoder-decoder using attention mechanism to address the aforementioned problem using Roman-Urdu and Urdu parallel corpus. To this end, we present (i) the first ever Roman-Urdu to Urdu parallel corpus of 1.1 million sentences, (ii) three state of the art encoder-decoder models, and (iii) a detailed empirical analysis of these three models on the Roman-Urdu to Urdu parallel corpus. Overall, attention-based model gives state-of-the-art performance with the benchmark of 70 BLEU score. Our qualitative experimental evaluation shows that our models generate coherent transliterations which are grammatically and logically correct.

A Knowledge-Based Machine Translation Using AI Technique

2018 ◽  
Vol 6 (3) ◽  
pp. 79-92
Author(s):  
Sahar A. El-Rahman ◽  
Tarek A. El-Shishtawy ◽  
Raafat A. El-Kammar
Keyword(s):  
Machine Translation ◽  
Target Language ◽  
Translation System ◽  
Module Structure ◽  
Source Language ◽  
Word Category ◽  
Knowledge Based ◽  
Language Analysis ◽  
Transfer Rules

This article presents a realistic technique for the machine aided translation system. In this technique, the system dictionary is partitioned into a multi-module structure for fast retrieval of Arabic features of English words. Each module is accessed through an interface that includes the necessary morphological rules, which directs the search toward the proper sub-dictionary. Another factor that aids fast retrieval of Arabic features of words is the prediction of the word category, and accesses its sub-dictionary to retrieve the corresponding attributes. The system consists of three main parts, which are the source language analysis, the transfer rules between source language (English) and target language (Arabic), and the generation of the target language. The proposed system is able to translate, some negative forms, demonstrations, and conjunctions, and also adjust nouns, verbs, and adjectives according their attributes. Then, it adds the symptom of Arabic words to generate a correct sentence.

scholarly journals Improving Neural Machine Translation by Filtering Synthetic Parallel Data

Entropy ◽  
2019 ◽  
Vol 21 (12) ◽  
pp. 1213
Author(s):  
Guanghao Xu ◽  
Youngjoong Ko ◽  
Jungyun Seo
Keyword(s):  
Machine Translation ◽  
Synthetic Data ◽  
Similarity Score ◽  
Target Language ◽  
Neural Machine Translation ◽  
Novel Approach ◽  
Parallel Data ◽  
Back Translation ◽  
Translation Errors ◽  
Training State

Synthetic data has been shown to be effective in training state-of-the-art neural machine translation (NMT) systems. Because the synthetic data is often generated by back-translating monolingual data from the target language into the source language, it potentially contains a lot of noise—weakly paired sentences or translation errors. In this paper, we propose a novel approach to filter this noise from synthetic data. For each sentence pair of the synthetic data, we compute a semantic similarity score using bilingual word embeddings. By selecting sentence pairs according to these scores, we obtain better synthetic parallel data. Experimental results on the IWSLT 2017 Korean→English translation task show that despite using much less data, our method outperforms the baseline NMT system with back-translation by up to 0.72 and 0.62 Bleu points for tst2016 and tst2017, respectively.

scholarly journals Synchronous Bidirectional Neural Machine Translation

2019 ◽  
Vol 7 ◽  
pp. 91-105 ◽  
Author(s):  
Long Zhou ◽  
Jiajun Zhang ◽  
Chengqing Zong
Keyword(s):  
Machine Translation ◽  
Large Scale ◽  
State Of The Art ◽  
Target Language ◽  
Single Model ◽  
Neural Machine Translation ◽  
German Translation ◽  
Transformer Model ◽  
Target Side ◽  
Future Information

Existing approaches to neural machine translation (NMT) generate the target language sequence token-by-token from left to right. However, this kind of unidirectional decoding framework cannot make full use of the target-side future contexts which can be produced in a right-to-left decoding direction, and thus suffers from the issue of unbalanced outputs. In this paper, we introduce a synchronous bidirectional–neural machine translation (SB-NMT) that predicts its outputs using left-to-right and right-to-left decoding simultaneously and interactively, in order to leverage both of the history and future information at the same time. Specifically, we first propose a new algorithm that enables synchronous bidirectional decoding in a single model. Then, we present an interactive decoding model in which left-to-right (right-to-left) generation does not only depend on its previously generated outputs, but also relies on future contexts predicted by right-to-left (left-to-right) decoding. We extensively evaluate the proposed SB-NMT model on large-scale NIST Chinese-English, WMT14 English-German, and WMT18 Russian-English translation tasks. Experimental results demonstrate that our model achieves significant improvements over the strong Transformer model by 3.92, 1.49, and 1.04 BLEU points, respectively, and obtains the state-of-the-art per- formance on Chinese-English and English- German translation tasks. 1

scholarly journals Query Expansion for Slovak to Bulgarian Language Machine Translation using Parallel Search

2021 ◽  
pp. 351-357
Author(s):  
VELISLAVA STOYKOVA ◽  
DANIELA MAJCHRAKOVA
Keyword(s):  
Machine Translation ◽  
Query Expansion ◽  
Statistical Approach ◽  
Semantic Relations ◽  
Target Language ◽  
Parallel Search ◽  
Keyword Query ◽  
Source Language ◽  
Standard Presentation ◽  
Standard Semantic

The paper presents results of the application of a statistical approach for Slovak to Bulgarian language machine translation. It uses Information Retrieval inspired search techniques and employs sever alalgorithmic steps of parallel statistical search with query expansion in Slovak-Bulgarian EUROPARL 7 Corpus using the Sketch Engine software and its scoring. The search includes the generation of concordances,collocations, word sketch differences, word sketches, and thesauri of the studied keyword (query) by using a statistical scoring, which is regarded as intermediate (inter-lingual) semantic standard presentation by means of which the studied keyword (from the source language) is mapped together with its possible translation equivalents (onto the target language. The results present the study of adjectival collocabillity in both Slovak and Bulgarian language from the corpus of political speech texts outlining the standard semantic relations based on the evaluation of statistical scoring. Finally, the advantages and shortcomings of the approach are discussed.

Sign in / Sign up

Export Citation Format

Share Document