scholarly journals Modeling Past and Future for Neural Machine Translation

2018 ◽  
Vol 6 ◽  
pp. 145-157 ◽  
Author(s):  
Zaixiang Zheng ◽  
Hao Zhou ◽  
Shujian Huang ◽  
Lili Mou ◽  
Xinyu Dai ◽  
...  
Keyword(s):  
Machine Translation ◽  
Alignment Error ◽  
Source Information ◽  
Neural Machine Translation ◽  
Attention Model ◽  
Translation Quality ◽  
The Past ◽  
Proposed Model ◽  
Coverage Model ◽  
Translation Systems

Existing neural machine translation systems do not explicitly model what has been translated and what has not during the decoding phase. To address this problem, we propose a novel mechanism that separates the source information into two parts: translated Past contents and untranslated Future contents, which are modeled by two additional recurrent layers. The Past and Future contents are fed to both the attention model and the decoder states, which provides Neural Machine Translation (NMT) systems with the knowledge of translated and untranslated contents. Experimental results show that the proposed approach significantly improves the performance in Chinese-English, German-English, and English-German translation tasks. Specifically, the proposed model outperforms the conventional coverage model in terms of both the translation quality and the alignment error rate.

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.

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

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 ◽  
Neural Machine 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.

scholarly journals Sublemma-Based Neural Machine Translation

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Thien Nguyen ◽  
Huu Nguyen ◽  
Phuoc Tran
Keyword(s):  
Machine Translation ◽  
Quality Data ◽  
Human Judgment ◽  
Linguistic Features ◽  
Neural Machine Translation ◽  
Low Resource ◽  
Part Of Speech ◽  
Proposed Model ◽  
Translation Systems ◽  
Ted Talks

Powerful deep learning approach frees us from feature engineering in many artificial intelligence tasks. The approach is able to extract efficient representations from the input data, if the data are large enough. Unfortunately, it is not always possible to collect large and quality data. For tasks in low-resource contexts, such as the Russian ⟶ Vietnamese machine translation, insights into the data can compensate for their humble size. In this study of modelling Russian ⟶ Vietnamese translation, we leverage the input Russian words by decomposing them into not only features but also subfeatures. First, we break down a Russian word into a set of linguistic features: part-of-speech, morphology, dependency labels, and lemma. Second, the lemma feature is further divided into subfeatures labelled with tags corresponding to their positions in the lemma. Being consistent with the source side, Vietnamese target sentences are represented as sequences of subtokens. Sublemma-based neural machine translation proves itself in our experiments on Russian-Vietnamese bilingual data collected from TED talks. Experiment results reveal that the proposed model outperforms the best available Russian  ⟶  Vietnamese model by 0.97 BLEU. In addition, automatic machine judgment on the experiment results is verified by human judgment. The proposed sublemma-based model provides an alternative to existing models when we build translation systems from an inflectionally rich language, such as Russian, Czech, or Bulgarian, in low-resource contexts.

scholarly journals Automatic evaluation of the quality of machine translation of a scientific text: the results of a five-year-long experiment

2021 ◽  
Vol 284 ◽  
pp. 08001
Author(s):  
Ilya Ulitkin ◽  
Irina Filippova ◽  
Natalia Ivanova ◽  
Alexey Poroykov
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Dramatic Improvement ◽  
Automatic Evaluation ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Automatic Translation ◽  
Translation Systems ◽  
Qualitative Changes

We report on various approaches to automatic evaluation of machine translation quality and describe three widely used methods. These methods, i.e. methods based on string matching and n-gram models, make it possible to compare the quality of machine translation to reference translation. We employ modern metrics for automatic evaluation of machine translation quality such as BLEU, F-measure, and TER to compare translations made by Google and PROMT neural machine translation systems with translations obtained 5 years ago, when statistical machine translation and rule-based machine translation algorithms were employed by Google and PROMT, respectively, as the main translation algorithms [6]. The evaluation of the translation quality of candidate texts generated by Google and PROMT with reference translation using an automatic translation evaluation program reveal significant qualitative changes as compared with the results obtained 5 years ago, which indicate a dramatic improvement in the work of the above-mentioned online translation systems. Ways to improve the quality of machine translation are discussed. It is shown that modern systems of automatic evaluation of translation quality allow errors made by machine translation systems to be identified and systematized, which will enable the improvement of the quality of translation by these systems in the future.

scholarly journals Balancing Quality and Human Involvement: An Effective Approach to Interactive Neural Machine Translation

2020 ◽  
Vol 34 (05) ◽  
pp. 9660-9667
Author(s):  
Tianxiang Zhao ◽  
Lemao Liu ◽  
Guoping Huang ◽  
Huayang Li ◽  
Yingling Liu ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Target Word ◽  
Machine Translation ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Proposed Model ◽  
Learning Technique ◽  
History Of ◽  
The Cost ◽  
Partial Translation

Conventional interactive machine translation typically requires a human translator to validate every generated target word, even though most of them are correct in the advanced neural machine translation (NMT) scenario. Previous studies have exploited confidence approaches to address the intensive human involvement issue, which request human guidance only for a few number of words with low confidences. However, such approaches do not take the history of human involvement into account, and optimize the models only for the translation quality while ignoring the cost of human involvement. In response to these pitfalls, we propose a novel interactive NMT model, which explicitly accounts the history of human involvements and particularly is optimized towards two objectives corresponding to the translation quality and the cost of human involvement, respectively. Specifically, the model jointly predicts a target word and a decision on whether to request human guidance, which is based on both the partial translation and the history of human involvements. Since there is no explicit signals on the decisions of requesting human guidance in the bilingual corpus, we optimize the model with the reinforcement learning technique which enables our model to accurately predict when to request human guidance. Simulated and real experiments show that the proposed model can achieve higher translation quality with similar or less human involvement over the confidence-based baseline.

scholarly journals Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior

2020 ◽  
Vol 34 (05) ◽  
pp. 8846-8853 ◽  
Author(s):  
Raphael Shu ◽  
Jason Lee ◽  
Hideki Nakayama ◽  
Kyunghyun Cho
Keyword(s):  
Machine Translation ◽  
Latent Variables ◽  
Latent Variable ◽  
Target Sequence ◽  
Inference Algorithm ◽  
Inference Procedure ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Proposed Model ◽  
Recent Refinement

Although neural machine translation models reached high translation quality, the autoregressive nature makes inference difficult to parallelize and leads to high translation latency. Inspired by recent refinement-based approaches, we propose LaNMT, a latent-variable non-autoregressive model with continuous latent variables and deterministic inference procedure. In contrast to existing approaches, we use a deterministic inference algorithm to find the target sequence that maximizes the lowerbound to the log-probability. During inference, the length of translation automatically adapts itself. Our experiments show that the lowerbound can be greatly increased by running the inference algorithm, resulting in significantly improved translation quality. Our proposed model closes the performance gap between non-autoregressive and autoregressive approaches on ASPEC Ja-En dataset with 8.6x faster decoding. On WMT'14 En-De dataset, our model narrows the gap with autoregressive baseline to 2.0 BLEU points with 12.5x speedup. By decoding multiple initial latent variables in parallel and rescore using a teacher model, the proposed model further brings the gap down to 1.0 BLEU point on WMT'14 En-De task with 6.8x speedup.

scholarly journals Neural Machine Translation with Key-Value Memory-Augmented Attention

2018 ◽  
Author(s):  
Fandong Meng ◽  
Zhaopeng Tu ◽  
Yong Cheng ◽  
Haiyang Wu ◽  
Junjie Zhai ◽  
...  
Keyword(s):  
Target Word ◽  
Machine Translation ◽  
English Translation ◽  
Translation Process ◽  
Neural Machine Translation ◽  
Attention Model ◽  
Proposed Model ◽  
Source Sentence ◽  
Remarkable Progress ◽  
Source Word

Although attention-based Neural Machine Translation (NMT) has achieved remarkable progress in recent years, it still suffers from issues of repeating and dropping translations. To alleviate these issues, we propose a novel key-value memory-augmented attention model for NMT, called KVMEMATT. Specifically, we maintain a timely updated keymemory to keep track of attention history and a fixed value-memory to store the representation of source sentence throughout the whole translation process. Via nontrivial transformations and iterative interactions between the two memories, the decoder focuses on more appropriate source word(s) for predicting the next target word at each decoding step, therefore can improve the adequacy of translations. Experimental results on Chinese)English and WMT17 German,English translation tasks demonstrate the superiority of the proposed model.

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 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.

Sign in / Sign up

Export Citation Format

Share Document