scholarly journals Open-Source Neural Machine Translation API Server

2017 ◽  
Vol 109 (1) ◽  
pp. 5-14
Author(s):  
Sander Tars ◽  
Kaspar Papli ◽  
Dmytro Chasovskyi ◽  
Mark Fishel
Keyword(s):  
Open Source ◽  
Machine Translation ◽  
Software Package ◽  
Web Application ◽  
Service Providers ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Open Api ◽  
Translation Service

Abstract We introduce an open-source implementation of a machine translation API server. The aim of this software package is to enable anyone to run their own multi-engine translation server with neural machine translation engines, supporting an open API for client applications. Besides the hub with the implementation of the client API and the translation service providers running in the background we also describe an open-source demo web application that uses our software package and implements an online translation tool that supports collecting translation quality comparisons from users.

scholarly journals Context-Aware Neural Machine Translation for Korean Honorific Expressions

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1589
Author(s):  
Yongkeun Hwang ◽  
Yanghoon Kim ◽  
Kyomin Jung
Keyword(s):  
Machine Translation ◽  
Deep Neural Networks ◽  
Contextual Information ◽  
Context Aware ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Sentence Level ◽  
Proposed Model ◽  
The Given ◽  
The Relationship

Neural machine translation (NMT) is one of the text generation tasks which has achieved significant improvement with the rise of deep neural networks. However, language-specific problems such as handling the translation of honorifics received little attention. In this paper, we propose a context-aware NMT to promote translation improvements of Korean honorifics. By exploiting the information such as the relationship between speakers from the surrounding sentences, our proposed model effectively manages the use of honorific expressions. Specifically, we utilize a novel encoder architecture that can represent the contextual information of the given input sentences. Furthermore, a context-aware post-editing (CAPE) technique is adopted to refine a set of inconsistent sentence-level honorific translations. To demonstrate the efficacy of the proposed method, honorific-labeled test data is required. Thus, we also design a heuristic that labels Korean sentences to distinguish between honorific and non-honorific styles. Experimental results show that our proposed method outperforms sentence-level NMT baselines both in overall translation quality and honorific translations.

Improving thai-lao neural machine translation with similarity lexicon

2021 ◽  
pp. 1-10
Author(s):  
Zhiqiang Yu ◽  
Yuxin Huang ◽  
Junjun Guo
Keyword(s):  
Machine Translation ◽  
Semantic Information ◽  
Neural Machine Translation ◽  
Low Resource ◽  
Translation Quality ◽  
Decoder Architecture ◽  
Baseline System ◽  
Input Sentence ◽  
Resource Conditions ◽  
Language Pair

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions. Thai-Lao is a typical low-resource language pair of tiny parallel corpus, leading to suboptimal NMT performance on it. However, Thai and Lao have considerable similarities in linguistic morphology and have bilingual lexicon which is relatively easy to obtain. To use this feature, we first build a bilingual similarity lexicon composed of pairs of similar words. Then we propose a novel NMT architecture to leverage the similarity between Thai and Lao. Specifically, besides the prevailing sentence encoder, we introduce an extra similarity lexicon encoder into the conventional encoder-decoder architecture, by which the semantic information carried by the similarity lexicon can be represented. We further provide a simple mechanism in the decoder to balance the information representations delivered from the input sentence and the similarity lexicon. Our approach can fully exploit linguistic similarity carried by the similarity lexicon to improve translation quality. Experimental results demonstrate that our approach achieves significant improvements over the state-of-the-art Transformer baseline system and previous similar works.

scholarly journals An Open-Source Web-Based Tool for Resource-Agnostic Interactive Translation Prediction

2014 ◽  
Vol 102 (1) ◽  
pp. 69-80 ◽  
Author(s):  
Torregrosa Daniel ◽  
Forcada Mikel L. ◽  
Pérez-Ortiz Juan Antonio
Keyword(s):  
Open Source ◽  
Machine Translation ◽  
Web Application ◽  
Statistical Machine Translation ◽  
Black Box ◽  
Translation System ◽  
Web Tool ◽  
Web Based ◽  
Strongly Coupled ◽  
Machine Translation System

Abstract We present a web-based open-source tool for interactive translation prediction (ITP) and describe its underlying architecture. ITP systems assist human translators by making context-based computer-generated suggestions as they type. Most of the ITP systems in literature are strongly coupled with a statistical machine translation system that is conveniently adapted to provide the suggestions. Our system, however, follows a resource-agnostic approach and suggestions are obtained from any unmodified black-box bilingual resource. This paper reviews our ITP method and describes the architecture of Forecat, a web tool, partly based on the recent technology of web components, that eases the use of our ITP approach in any web application requiring this kind of translation assistance. We also evaluate the performance of our method when using an unmodified Moses-based statistical machine translation system as the bilingual resource.

scholarly journals OpenNMT: Open-Source Toolkit for Neural Machine Translation

2017 ◽  
Author(s):  
Guillaume Klein ◽  
Yoon Kim ◽  
Yuntian Deng ◽  
Jean Senellart ◽  
Alexander Rush
Keyword(s):  
Open Source ◽  
Machine Translation ◽  
Neural Machine Translation

scholarly journals Recurrent Stacking of Layers for Compact Neural Machine Translation Models

2019 ◽  
Vol 33 ◽  
pp. 6292-6299 ◽  
Author(s):  
Raj Dabre ◽  
Atsushi Fujita
Keyword(s):  
Machine Translation ◽  
Single Layer ◽  
Training Data ◽  
Neural Machine Translation ◽  
Parallel Corpora ◽  
Translation Quality ◽  
Sequence Generation ◽  
Sequence Modeling ◽  
Back Translation

In encoder-decoder based sequence-to-sequence modeling, the most common practice is to stack a number of recurrent, convolutional, or feed-forward layers in the encoder and decoder. While the addition of each new layer improves the sequence generation quality, this also leads to a significant increase in the number of parameters. In this paper, we propose to share parameters across all layers thereby leading to a recurrently stacked sequence-to-sequence model. We report on an extensive case study on neural machine translation (NMT) using our proposed method, experimenting with a variety of datasets. We empirically show that the translation quality of a model that recurrently stacks a single-layer 6 times, despite its significantly fewer parameters, approaches that of a model that stacks 6 different layers. We also show how our method can benefit from a prevalent way for improving NMT, i.e., extending training data with pseudo-parallel corpora generated by back-translation. We then analyze the effects of recurrently stacked layers by visualizing the attentions of models that use recurrently stacked layers and models that do not. Finally, we explore the limits of parameter sharing where we share even the parameters between the encoder and decoder in addition to recurrent stacking of layers.

scholarly journals Is automation changing the translation profession?

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Anthony Pym ◽  
Ester Torres-Simón
Keyword(s):  
Machine Translation ◽  
Communication Skills ◽  
Service Providers ◽  
Time Data ◽  
Market Segments ◽  
Interactive Communication ◽  
Neural Machine Translation ◽  
History Of ◽  
Translation Services ◽  
Translation Systems

Abstract As a language-intensive profession, translation is of frontline interest in the era of language automation. In particular, the development of neural machine translation systems since 2016 has brought with it fears that soon there will be no more human translators. When considered in terms of the history of automation, however, any such direct effect is far from obvious: the translation industry is still growing and machine translation is only one instance of automation. At the same time, data on remuneration indicate structural wage dispersion in professional translation services, with some signs that this dispersion may increase in certain market segments as automated workflows and translation technologies are adopted more by large language-service providers more than by smaller companies and individual freelancers. An analysis of recent changes in discourses on and in the translation profession further indicates conceptual adjustments in the profession that may be attributed to growing automation, particularly with respect to expanding skills set associated with translation, the tendency to combine translation with other forms of communication, and the use of interactive communication skills to authorize and humanize the results of automation.

scholarly journals Knowledge Graphs Enhanced Neural Machine Translation

2020 ◽  
Author(s):  
Yang Zhao ◽  
Jiajun Zhang ◽  
Yu Zhou ◽  
Chengqing Zong
Keyword(s):  
Machine Translation ◽  
Semantic Space ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Structured Information ◽  
Knowledge Graphs ◽  
Japanese Translation

Knowledge graphs (KGs) store much structured information on various entities, many of which are not covered by the parallel sentence pairs of neural machine translation (NMT). To improve the translation quality of these entities, in this paper we propose a novel KGs enhanced NMT method. Specifically, we first induce the new translation results of these entities by transforming the source and target KGs into a unified semantic space. We then generate adequate pseudo parallel sentence pairs that contain these induced entity pairs. Finally, NMT model is jointly trained by the original and pseudo sentence pairs. The extensive experiments on Chinese-to-English and Englishto-Japanese translation tasks demonstrate that our method significantly outperforms the strong baseline models in translation quality, especially in handling the induced entities.

Enhancing Lexical Translation Consistency for Document-Level Neural Machine Translation

2022 ◽  
Vol 21 (3) ◽  
pp. 1-21
Author(s):  
Xiaomian Kang ◽  
Yang Zhao ◽  
Jiajun Zhang ◽  
Chengqing Zong
Keyword(s):  
Machine Translation ◽  
English Translation ◽  
Test Set ◽  
Neural Machine Translation ◽  
Global Context ◽  
Translation Quality ◽  
Sentence Level ◽  
Document Level

Document-level neural machine translation (DocNMT) has yielded attractive improvements. In this article, we systematically analyze the discourse phenomena in Chinese-to-English translation, and focus on the most obvious ones, namely lexical translation consistency. To alleviate the lexical inconsistency, we propose an effective approach that is aware of the words which need to be translated consistently and constrains the model to produce more consistent translations. Specifically, we first introduce a global context extractor to extract the document context and consistency context, respectively. Then, the two types of global context are integrated into a encoder enhancer and a decoder enhancer to improve the lexical translation consistency. We create a test set to evaluate the lexical consistency automatically. Experiments demonstrate that our approach can significantly alleviate the lexical translation inconsistency. In addition, our approach can also substantially improve the translation quality compared to sentence-level Transformer.

scholarly journals Integration of a Multilingual Preordering Component into a Commercial SMT Platform

2017 ◽  
Vol 108 (1) ◽  
pp. 61-72
Author(s):  
Anita Ramm ◽  
Riccardo Superbo ◽  
Dimitar Shterionov ◽  
Tony O’Dowd ◽  
Alexander Fraser
Keyword(s):  
Open Source ◽  
Machine Translation ◽  
Long Range ◽  
Significant Role ◽  
Processing Speed ◽  
Statistical Machine Translation ◽  
Neural Machine Translation ◽  
Open Source Tool

AbstractWe present a multilingual preordering component tailored for a commercial Statistical Machine translation platform. In commercial settings, issues such as processing speed as well as the ability to adapt models to the customers’ needs play a significant role and have a big impact on the choice of approaches that are added to the custom pipeline to deal with specific problems such as long-range reorderings.We developed a fast and customisable preordering component, also available as an open-source tool, which comes along with a generic implementation that is restricted neither to the translation platform nor to the Machine Translation paradigm. We test preordering on three language pairs: English →Japanese/German/Chinese for both Statistical Machine Translation (SMT) and Neural Machine Translation (NMT). Our experiments confirm previously reported improvements in the SMT output when the models are trained on preordered data, but they also show that preordering does not improve NMT.

Estimating Machine Translation Quality of Any Input Sentence

2020 ◽  
Vol 30 (01) ◽  
pp. 2050002
Author(s):  
Taichi Aida ◽  
Kazuhide Yamamoto
Keyword(s):  
Machine Translation ◽  
Evaluation Model ◽  
Joint Probability ◽  
Translation System ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Machine Translation System ◽  
Input Sentence ◽  
The One

Current methods of neural machine translation may generate sentences with different levels of quality. Methods for automatically evaluating translation output from machine translation can be broadly classified into two types: a method that uses human post-edited translations for training an evaluation model, and a method that uses a reference translation that is the correct answer during evaluation. On the one hand, it is difficult to prepare post-edited translations because it is necessary to tag each word in comparison with the original translated sentences. On the other hand, users who actually employ the machine translation system do not have a correct reference translation. Therefore, we propose a method that trains the evaluation model without using human post-edited sentences and in the test set, estimates the quality of output sentences without using reference translations. We define some indices and predict the quality of translations with a regression model. For the quality of the translated sentences, we employ the BLEU score calculated from the number of word [Formula: see text]-gram matches between the translated sentence and the reference translation. After that, we compute the correlation between quality scores predicted by our method and BLEU actually computed from references. According to the experimental results, the correlation with BLEU is the highest when XGBoost uses all the indices. Moreover, looking at each index, we find that the sentence log-likelihood and the model uncertainty, which are based on the joint probability of generating the translated sentence, are important in BLEU estimation.

Sign in / Sign up

Export Citation Format

Share Document