Investigating post-editing effort

2021 ◽  
Vol 8 (2) ◽  
pp. 378-403
Author(s):  
Maria Stasimioti ◽  
Vilelmini Sosoni ◽  
Konstantinos Chatzitheodorou
Keyword(s):  
Machine Translation ◽  
First Language ◽  
Working Environment ◽  
Translation Product ◽  
Greek Language ◽  
Neural Machine Translation ◽  
Product And Process ◽  
Technical Effort ◽  
Language Pair

Abstract The working environment of translators has changed significantly in recent decades, with post-editing (PE) emerging as a new trend in the human translation workflow, particularly following the advent of neural machine translation (NMT) and the improvement of the quality of the machine translation (MT) raw output especially at the level of fluency. In addition, the directionality axiom is increasingly being questioned with translators working from and into their first language both in the context of translation (Buchweitz and Alves 2006; Pavlović and Jensen 2009; Fonseca and Barbosa 2015; Hunziker Heeb 2015; Ferreira 2013, 2014; Ferreira et al. 2016; Feng 2017) and in the context of PE (Garcia 2011; Sánchez-Gijón and Torres-Hostench 2014; da Silva et al. 2017; Toledo Báez 2018). In this study we employ product- and process-oriented approaches to investigate directionality in PE in the English-Greek language pair. In particular, we compare the cognitive, temporal, and technical effort expended by translators for the full PE of NMT output in L1 (Greek) with the effort required for the full PE of NMT output in L2 (English), while we also analyze the quality of the final translation product. Our findings reveal that PE in L2, i.e., inverse PE, is less demanding than PE in L1, i.e., direct PE, in terms of the time and keystrokes required, and the cognitive load exerted on translators. Finally, our research shows that directionality does not imply differences in quality.

An Improved English-to-Mizo Neural Machine Translation

2021 ◽  
Vol 20 (4) ◽  
pp. 1-21
Author(s):  
Candy Lalrempuii ◽  
Badal Soni ◽  
Partha Pakray
Keyword(s):  
Machine Translation ◽  
Model Performance ◽  
Sentence Length ◽  
Prediction Errors ◽  
Indian Languages ◽  
Neural Machine Translation ◽  
Automatic Translation ◽  
Translation Techniques ◽  
Language Pair

Machine Translation is an effort to bridge language barriers and misinterpretations, making communication more convenient through the automatic translation of languages. The quality of translations produced by corpus-based approaches predominantly depends on the availability of a large parallel corpus. Although machine translation of many Indian languages has progressively gained attention, there is very limited research on machine translation and the challenges of using various machine translation techniques for a low-resource language such as Mizo. In this article, we have implemented and compared statistical-based approaches with modern neural-based approaches for the English–Mizo language pair. We have experimented with different tokenization methods, architectures, and configurations. The performance of translations predicted by the trained models has been evaluated using automatic and human evaluation measures. Furthermore, we have analyzed the prediction errors of the models and the quality of predictions based on variations in sentence length and compared the model performance with the existing baselines.

scholarly journals Evaluation of English–Slovak Neural and Statistical Machine Translation

2021 ◽  
Vol 11 (7) ◽  
pp. 2948
Author(s):  
Lucia Benkova ◽  
Dasa Munkova ◽  
Ľubomír Benko ◽  
Michal Munk
Keyword(s):  
Machine Translation ◽  
Statistical Approach ◽  
Statistical Machine Translation ◽  
Specific Domain ◽  
Neural Network Approach ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
The Neural Network ◽  
Language Pair

This study is focused on the comparison of phrase-based statistical machine translation (SMT) systems and neural machine translation (NMT) systems using automatic metrics for translation quality evaluation for the language pair of English and Slovak. As the statistical approach is the predecessor of neural machine translation, it was assumed that the neural network approach would generate results with a better quality. An experiment was performed using residuals to compare the scores of automatic metrics of the accuracy (BLEU_n) of the statistical machine translation with those of the neural machine translation. The results showed that the assumption of better neural machine translation quality regardless of the system used was confirmed. There were statistically significant differences between the SMT and NMT in favor of the NMT based on all BLEU_n scores. The neural machine translation achieved a better quality of translation of journalistic texts from English into Slovak, regardless of if it was a system trained on general texts, such as Google Translate, or specific ones, such as the European Commission’s (EC’s) tool, which was trained on a specific-domain.

scholarly journals Fully Character-Level Neural Machine Translation without Explicit Segmentation

2017 ◽  
Vol 5 ◽  
pp. 365-378 ◽  
Author(s):  
Jason Lee ◽  
Kyunghyun Cho ◽  
Thomas Hofmann
Keyword(s):  
Machine Translation ◽  
Convolutional Network ◽  
Neural Machine Translation ◽  
Single Character ◽  
Comparable Performance ◽  
Translation Systems ◽  
Multiple Languages ◽  
Character Sequence ◽  
Language Pair

Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to a target character sequence without any segmentation. We employ a character-level convolutional network with max-pooling at the encoder to reduce the length of source representation, allowing the model to be trained at a speed comparable to subword-level models while capturing local regularities. Our character-to-character model outperforms a recently proposed baseline with a subword-level encoder on WMT’15 DE-EN and CS-EN, and gives comparable performance on FI-EN and RU-EN. We then demonstrate that it is possible to share a single character-level encoder across multiple languages by training a model on a many-to-one translation task. In this multilingual setting, the character-level encoder significantly outperforms the subword-level encoder on all the language pairs. We observe that on CS-EN, FI-EN and RU-EN, the quality of the multilingual character-level translation even surpasses the models specifically trained on that language pair alone, both in terms of the BLEU score and human judgment.

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 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 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.

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