Non-autoregressive neural machine translation with auxiliary representation fusion

2021 ◽  
pp. 1-11
Author(s):  
Quan Du ◽  
Kai Feng ◽  
Chen Xu ◽  
Tong Xiao ◽  
Jingbo Zhu
Keyword(s):  
Machine Translation ◽  
Experimental Results ◽  
The Other ◽  
Generation Process ◽  
Neural Machine Translation ◽  
Trade Off ◽  
Translation Quality ◽  
Other Hand ◽  
Entire Sequence ◽  
Translation Accuracy

Recently, many efforts have been devoted to speeding up neural machine translation models. Among them, the non-autoregressive translation (NAT) model is promising because it removes the sequential dependence on the previously generated tokens and parallelizes the generation process of the entire sequence. On the other hand, the autoregressive translation (AT) model in general achieves a higher translation accuracy than the NAT counterpart. Therefore, a natural idea is to fuse the AT and NAT models to seek a trade-off between inference speed and translation quality. This paper proposes an ARF-NAT model (NAT with auxiliary representation fusion) to introduce the merit of a shallow AT model to an NAT model. Three functions are designed to fuse the auxiliary representation into the decoder of the NAT model. Experimental results show that ARF-NAT outperforms the NAT baseline by 5.26 BLEU scores on the WMT’14 German-English task with a significant speedup (7.58 times) over several strong AT baselines.

scholarly journals Machine translation of English content: A comparative study of different methods

2021 ◽  
Vol 30 (1) ◽  
pp. 980-987
Author(s):  
Jinfeng Xue
Keyword(s):  
Comparative Study ◽  
Machine Translation ◽  
Experimental Results ◽  
The Other ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Operation Speed ◽  
Two Systems

Abstract Based on neural machine translation, this article introduced the ConvS2S system and transformer system, designed a semantic sharing combined transformer system to improve translation quality, and compared the three systems on the NIST dataset. The results showed that the operation speed of the semantic sharing combined transformer system was the highest, reaching 3934.27 words per second; the BLEU value of the ConvS2S system was the smallest, followed by the transformer system and the semantic sharing combined transformer system. Taking NIST08 as an example, the BLEU values of the designed system were 4.74 and 1.49 higher than the other two systems. The analysis of examples showed that the semantic sharing combined transformer had higher translation quality. The experimental results show that the proposed system is reliable in English content translation and can be further promoted and applied in practice.

Unsupervised Translation Quality Estimation for Digital Entertainment Content Subtitles

2020 ◽  
Vol 14 (01) ◽  
pp. 137-151
Author(s):  
Prabhakar Gupta ◽  
Mayank Sharma
Keyword(s):  
Machine Translation ◽  
Experimental Results ◽  
Parallel Translation ◽  
Word Embeddings ◽  
Quality Estimation ◽  
Neural Machine Translation ◽  
Intensity Index ◽  
Translation Quality ◽  
Digital Entertainment ◽  
Reference Corpus

We demonstrate the potential for using aligned bilingual word embeddings in developing an unsupervised method to evaluate machine translations without a need for parallel translation corpus or reference corpus. We explain different aspects of digital entertainment content subtitles. We share our experimental results for four languages pairs English to French, German, Portuguese, Spanish, and present findings on the shortcomings of Neural Machine Translation for subtitles. We propose several improvements over the system designed by Gupta et al. [P. Gupta, S. Shekhawat and K. Kumar, Unsupervised quality estimation without reference corpus for subtitle machine translation using word embeddings, IEEE 13th Int. Conf. Semantic Computing, 2019, pp. 32–38.] by incorporating custom embedding model curated to subtitles, compound word splits and punctuation inclusion. We show a massive run time improvement of the order of [Formula: see text] by considering three types of edits, removing Proximity Intensity Index (PII) and changing post-edit score calculation from their system.

scholarly journals Synthesizing Parallel Data of User-Generated Texts with Zero-Shot Neural Machine Translation

2020 ◽  
Vol 8 ◽  
pp. 710-725
Author(s):  
Benjamin Marie ◽  
Atsushi Fujita
Keyword(s):  
Social Media ◽  
Machine Translation ◽  
Language Model ◽  
The Other ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Online Social Media ◽  
Parallel Data

Neural machine translation (NMT) systems are usually trained on clean parallel data. They can perform very well for translating clean in-domain texts. However, as demonstrated by previous work, the translation quality significantly worsens when translating noisy texts, such as user-generated texts (UGT) from online social media. Given the lack of parallel data of UGT that can be used to train or adapt NMT systems, we synthesize parallel data of UGT, exploiting monolingual data of UGT through crosslingual language model pre-training and zero-shot NMT systems. This paper presents two different but complementary approaches: One alters given clean parallel data into UGT-like parallel data whereas the other generates translations from monolingual data of UGT. On the MTNT translation tasks, we show that our synthesized parallel data can lead to better NMT systems for UGT while making them more robust in translating texts from various domains and styles.

scholarly journals Ethical Issues of Neural Machine Translation

2020 ◽  
Vol 15 ◽  
pp. 81-83
Author(s):  
Serhii Zasiekin ◽  
Solomiia Vakuliuk
Keyword(s):  
Machine Translation ◽  
Ethical Issues ◽  
Point Of View ◽  
The Other ◽  
Neural Machine Translation ◽  
Translation Tools ◽  
Other Hand ◽  
Ethical Point ◽  
Translation Ethics

The paper is focused on the issues of machine translation ethics. The goal of the present study is to discuss the role of neural machine translation tools from an ethical point of view and their impact on humans. Although traditionally ethics of translation is viewed in terms of sameness and difference, it is human translator who is a party to ethics of translation. It is discussed that translators should rely on technology as a helpful leverage in their job, since it allows them to be faster and more productive. On the other hand, we take an interest in examining the extent to which translation technology tools are given power. Neural machine translators can be unsupervised by humans, therefore viewed as a party to ethics of translation.

scholarly journals Neural Machine Translation with Error Correction

2020 ◽  
Author(s):  
Kaitao Song ◽  
Xu Tan ◽  
Jianfeng Lu
Keyword(s):  
Error Correction ◽  
Machine Translation ◽  
Error Propagation ◽  
Ground Truth ◽  
Prediction Errors ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Error Correction Mechanism ◽  
Experimental Analyses ◽  
Translation Accuracy

Neural machine translation (NMT) generates the next target token given as input the previous ground truth target tokens during training while the previous generated target tokens during inference, which causes discrepancy between training and inference as well as error propagation, and affects the translation accuracy. In this paper, we introduce an error correction mechanism into NMT, which corrects the error information in the previous generated tokens to better predict the next token. Specifically, we introduce two-stream self-attention from XLNet into NMT decoder, where the query stream is used to predict the next token, and meanwhile the content stream is used to correct the error information from the previous predicted tokens. We leverage scheduled sampling to simulate the prediction errors during training. Experiments on three IWSLT translation datasets and two WMT translation datasets demonstrate that our method achieves improvements over Transformer baseline and scheduled sampling. Further experimental analyses also verify the effectiveness of our proposed error correction mechanism to improve the translation quality.

scholarly journals Semantic Neural Machine Translation Using AMR

2019 ◽  
Vol 7 ◽  
pp. 19-31 ◽  
Author(s):  
Linfeng Song ◽  
Daniel Gildea ◽  
Yue Zhang ◽  
Zhiguo Wang ◽  
Jinsong Su
Keyword(s):  
Machine Translation ◽  
The Other ◽  
Standard English ◽  
Semantic Representations ◽  
Data Sparsity ◽  
Neural Machine Translation ◽  
Translation Model ◽  
Other Hand ◽  
Meaning Representation

It is intuitive that semantic representations can be useful for machine translation, mainly because they can help in enforcing meaning preservation and handling data sparsity (many sentences correspond to one meaning) of machine translation models. On the other hand, little work has been done on leveraging semantics for neural machine translation (NMT). In this work, we study the usefulness of AMR (abstract meaning representation) on NMT. Experiments on a standard English-to-German dataset show that incorporating AMR as additional knowledge can significantly improve a strong attention-based sequence-to-sequence neural translation model.

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.

Natural Vulcanization Accelerators in Hevea Latex

1948 ◽  
Vol 21 (4) ◽  
pp. 853-859
Author(s):  
R. F. A. Altman
Keyword(s):  
Amino Acids ◽  
Experimental Results ◽  
The Other ◽  
Active Nitrogen ◽  
Nitrogen Bases ◽  
Other Hand ◽  
Decomposition Processes ◽  
Volatile Products ◽  
Nitrogenous Substances ◽  
The One

Abstract As numerous investigators have shown, some of the nonrubber components of Hevea latex have a decided accelerating action on the process of vulcanization. A survey of the literature on this subject points to the validity of certain general facts. 1. Among the nonrubber components of latex which have been investigated, certain nitrogenous bases appear to be most important for accelerating the rate of vulcanization. 2. These nitrogen bases apparently occur partly naturally in fresh latex, and partly as the result of putrefaction, heating, and other decomposition processes. 3. The nitrogen bases naturally present in fresh latex at later stages have been identified by Altman to be trigonelline, stachhydrine, betonicine, choline, methylamine, trimethylamine, and ammonia. These bases are markedly active in vulcanization, as will be seen in the section on experimental results. 4. The nitrogenous substances formed by the decomposition processes have only partly been identified, on the one hand as tetra- and pentamethylene diamine and some amino acids, on the other hand as alkaloids, proline, diamino acids, etc. 5. It has been generally accepted that these nitrogenous substances are derived from the proteins of the latex. 6. Decomposition appears to be connected with the formation of a considerable amount of acids. 7. The production of volatile nitrogen bases as a rule accompanies the decomposition processes. These volatile products have not been identified. 8. The active nitrogen bases, either already formed or derived from complex nitrogenous substances, seem to be soluble in water but only slightly soluble in acetone.

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.

Improved neural machine translation for low-resource English–Assamese pair

2021 ◽  
pp. 1-12
Author(s):  
Sahinur Rahman Laskar ◽  
Abdullah Faiz Ur Rahman Khilji ◽  
Partha Pakray ◽  
Sivaji Bandyopadhyay
Keyword(s):  
Machine Translation ◽  
Data Augmentation ◽  
Language Translation ◽  
Linguistically Diverse ◽  
Neural Machine Translation ◽  
Low Resource ◽  
Parallel Data ◽  
The World ◽  
Translation Accuracy ◽  
Vocabulary Problems

Language translation is essential to bring the world closer and plays a significant part in building a community among people of different linguistic backgrounds. Machine translation dramatically helps in removing the language barrier and allows easier communication among linguistically diverse communities. Due to the unavailability of resources, major languages of the world are accounted as low-resource languages. This leads to a challenging task of automating translation among various such languages to benefit indigenous speakers. This article investigates neural machine translation for the English–Assamese resource-poor language pair by tackling insufficient data and out-of-vocabulary problems. We have also proposed an approach of data augmentation-based NMT, which exploits synthetic parallel data and shows significantly improved translation accuracy for English-to-Assamese and Assamese-to-English translation and obtained state-of-the-art results.

Sign in / Sign up

Export Citation Format

Share Document