A Survey on Document-level Neural Machine Translation

2021 ◽  
Vol 54 (2) ◽  
pp. 1-36
Author(s):  
Sameen Maruf ◽  
Fahimeh Saleh ◽  
Gholamreza Haffari
Keyword(s):  
Machine Translation ◽  
Language Processing ◽  
Research Field ◽  
Translation Process ◽  
Future Directions ◽  
Translation Quality ◽  
Current State ◽  
Evaluation Strategies ◽  
Almost All ◽  
Document Level

Machine translation (MT) is an important task in natural language processing (NLP), as it automates the translation process and reduces the reliance on human translators. With the resurgence of neural networks, the translation quality surpasses that of the translations obtained using statistical techniques for most language-pairs. Up until a few years ago, almost all of the neural translation models translated sentences independently , without incorporating the wider document-context and inter-dependencies among the sentences. The aim of this survey article is to highlight the major works that have been undertaken in the space of document-level machine translation after the neural revolution, so researchers can recognize the current state and future directions of this field. We provide an organization of the literature based on novelties in modelling and architectures as well as training and decoding strategies. In addition, we cover evaluation strategies that have been introduced to account for the improvements in document MT, including automatic metrics and discourse-targeted test sets. We conclude by presenting possible avenues for future exploration in this research field.

scholarly journals Ethical issues on artificial intelligence in radiology: how is it reported in research articles? The current state and future directions

2021 ◽  
Vol 90 (2) ◽  
pp. e513
Author(s):  
Tomasz Piotrowski ◽  
Joanna Kazmierska ◽  
Mirosława Mocydlarz-Adamcewicz ◽  
Adam Ryczkowski
Keyword(s):  
Artificial Intelligence ◽  
Ethical Issues ◽  
Real Life ◽  
Exclusion Criteria ◽  
Future Directions ◽  
Current State ◽  
Ethical Status ◽  
The Status ◽  
Clinical Questions ◽  
Almost All

Background. This paper evaluates the status of reporting information related to the usage and ethical issues of artificial intelligence (AI) procedures in clinical trial (CT) papers focussed on radiology issues as well as other (non-trial) original radiology articles (OA). Material and Methods. The evaluation was performed by three independent observers who were, respectively physicist, physician and computer scientist. The analysis was performed for two groups of publications, i.e., for CT and OA. Each group included 30 papers published from 2018 to 2020, published before guidelines proposed by Liu et al. (Nat Med. 2020; 26:1364-1374). The set of items used to catalogue and to verify the ethical status of the AI reporting was developed using the above-mentioned guidelines. Results. Most of the reviewed studies, clearly stated their use of AI methods and more importantly, almost all tried to address relevant clinical questions. Although in most of the studies, patient inclusion and exclusion criteria were presented, the widespread lack of rigorous descriptions of the study design apart from a detailed explanation of the AI approach itself is noticeable. Few of the chosen studies provided information about anonymization of data and the process of secure data sharing. Only a few studies explore the patterns of incorrect predictions by the proposed AI tools and their possible reasons. Conclusion. Results of review support idea of implementation of uniform guidelines for designing and reporting studies with use of AI tools. Such guidelines help to design robust, transparent and reproducible tools for use in real life.

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.

Machine Learning Approaches for Bangla Statistical Machine Translation

2013 ◽  
pp. 79-95
Author(s):  
Maxim Roy
Keyword(s):  
Machine Learning ◽  
Active Learning ◽  
Machine Translation ◽  
Language Processing ◽  
Statistical Machine Translation ◽  
Low Density ◽  
Learning Approaches ◽  
Translation Quality ◽  
Selection Strategies ◽  
Translation Accuracy

Machine Translation (MT) from Bangla to English has recently become a priority task for the Bangla Natural Language Processing (NLP) community. Statistical Machine Translation (SMT) systems require a significant amount of bilingual data between language pairs to achieve significant translation accuracy. However, being a low-density language, such resources are not available in Bangla. In this chapter, the authors discuss how machine learning approaches can help to improve translation quality within as SMT system without requiring a huge increase in resources. They provide a novel semi-supervised learning and active learning framework for SMT, which utilizes both labeled and unlabeled data. The authors discuss sentence selection strategies in detail and perform detailed experimental evaluations on the sentence selection methods. In semi-supervised settings, reversed model approach outperformed all other approaches for Bangla-English SMT, and in active learning setting, geometric 4-gram and geometric phrase sentence selection strategies proved most useful based on BLEU score results over baseline approaches. Overall, in this chapter, the authors demonstrate that for low-density language like Bangla, these machine-learning approaches can improve translation quality.

scholarly journals Machine Learning Interpretability: A Survey on Methods and Metrics

Electronics ◽  
2019 ◽  
Vol 8 (8) ◽  
pp. 832 ◽  
Author(s):  
Diogo V. Carvalho ◽  
Eduardo M. Pereira ◽  
Jaime S. Cardoso
Keyword(s):  
Machine Learning ◽  
Social Impact ◽  
Research Field ◽  
Learning Systems ◽  
Future Directions ◽  
The Past ◽  
Current State ◽  
Black Boxes ◽  
Interpretable Models

Machine learning systems are becoming increasingly ubiquitous. These systems’s adoption has been expanding, accelerating the shift towards a more algorithmic society, meaning that algorithmically informed decisions have greater potential for significant social impact. However, most of these accurate decision support systems remain complex black boxes, meaning their internal logic and inner workings are hidden to the user and even experts cannot fully understand the rationale behind their predictions. Moreover, new regulations and highly regulated domains have made the audit and verifiability of decisions mandatory, increasing the demand for the ability to question, understand, and trust machine learning systems, for which interpretability is indispensable. The research community has recognized this interpretability problem and focused on developing both interpretable models and explanation methods over the past few years. However, the emergence of these methods shows there is no consensus on how to assess the explanation quality. Which are the most suitable metrics to assess the quality of an explanation? The aim of this article is to provide a review of the current state of the research field on machine learning interpretability while focusing on the societal impact and on the developed methods and metrics. Furthermore, a complete literature review is presented in order to identify future directions of work on this field.

scholarly journals Neural Machine Translation with Byte-Level Subwords

2020 ◽  
Vol 34 (05) ◽  
pp. 9154-9160
Author(s):  
Changhan Wang ◽  
Kyunghyun Cho ◽  
Jiatao Gu
Keyword(s):  
Machine Translation ◽  
Computational Cost ◽  
Potential Solution ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Comparable Performance ◽  
Almost All ◽  
Noisy Text ◽  
High Computational Cost

Almost all existing machine translation models are built on top of character-based vocabularies: characters, subwords or words. Rare characters from noisy text or character-rich languages such as Japanese and Chinese however can unnecessarily take up vocabulary slots and limit its compactness. Representing text at the level of bytes and using the 256 byte set as vocabulary is a potential solution to this issue. High computational cost has however prevented it from being widely deployed or used in practice. In this paper, we investigate byte-level subwords, specifically byte-level BPE (BBPE), which is compacter than character vocabulary and has no out-of-vocabulary tokens, but is more efficient than using pure bytes only is. We claim that contextualizing BBPE embeddings is necessary, which can be implemented by a convolutional or recurrent layer. Our experiments show that BBPE has comparable performance to BPE while its size is only 1/8 of that for BPE. In the multilingual setting, BBPE maximizes vocabulary sharing across many languages and achieves better translation quality. Moreover, we show that BBPE enables transferring models between languages with non-overlapping character sets.

scholarly journals A Systematic Review of Machine Learning Algorithms in Cyberbullying Detection: Future Directions and Challenges

2021 ◽  
Vol 4 (1) ◽  
pp. 01-26
Author(s):  
Muhammad Arif
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Social Media ◽  
Language Processing ◽  
Machine Learning Algorithms ◽  
Future Directions ◽  
Social Media Networks ◽  
Current State ◽  
Art Research ◽  
Cyberbullying Detection

Social media networks are becoming an essential part of life for most of the world’s population. Detecting cyberbullying using machine learning and natural language processing algorithms is getting the attention of researchers. There is a growing need for automatic detection and mitigation of cyberbullying events on social media. In this study, research directions and the theoretical foundation in this area are investigated. A systematic review of the current state-of-the-art research in this area is conducted. A framework considering all possible actors in the cyberbullying event must be designed, including various aspects of cyberbullying and its effect on the participating actors. Furthermore, future directions and challenges are also discussed.

scholarly journals Use of Artificial Intelligence in Nononcologic Interventional Radiology: Current State and Future Directions

2021 ◽  
Author(s):  
Rohil Malpani ◽  
Christopher W. Petty ◽  
Neha Bhatt ◽  
Lawrence H. Staib ◽  
Julius Chapiro
Keyword(s):  
Artificial Intelligence ◽  
Clinical Practice ◽  
Language Processing ◽  
Vascular Imaging ◽  
Future Directions ◽  
Current State ◽  
The Future ◽  
Procedural Planning ◽  
Applications Of Ai

AbstractThe future of radiology is disproportionately linked to the applications of artificial intelligence (AI). Recent exponential advancements in AI are already beginning to augment the clinical practice of radiology. Driven by a paucity of review articles in the area, this article aims to discuss applications of AI in nononcologic IR across procedural planning, execution, and follow-up along with a discussion on the future directions of the field. Applications in vascular imaging, radiomics, touchless software interactions, robotics, natural language processing, postprocedural outcome prediction, device navigation, and image acquisition are included. Familiarity with AI study analysis will help open the current “black box” of AI research and help bridge the gap between the research laboratory and clinical practice.

scholarly journals Modern Scientific Visualizations on the Web

Informatics ◽  
2020 ◽  
Vol 7 (4) ◽  
pp. 37
Author(s):  
Loraine Franke ◽  
Daniel Haehn
Keyword(s):  
Scientific Visualization ◽  
State Of The Art ◽  
Three Dimensional ◽  
Emerging Technology ◽  
Research Field ◽  
Future Directions ◽  
Web Based ◽  
Current State ◽  
Visualization Systems ◽  
The Web

Modern scientific visualization is web-based and uses emerging technology such as WebGL (Web Graphics Library) and WebGPU for three-dimensional computer graphics and WebXR for augmented and virtual reality devices. These technologies, paired with the accessibility of websites, potentially offer a user experience beyond traditional standalone visualization systems. We review the state-of-the-art of web-based scientific visualization and present an overview of existing methods categorized by application domain. As part of this analysis, we introduce the Scientific Visualization Future Readiness Score (SciVis FRS) to rank visualizations for a technology-driven disruptive tomorrow. We then summarize challenges, current state of the publication trend, future directions, and opportunities for this exciting research field.

Computational Linguistics

2018 ◽  
Author(s):  
Karine Megerdoomian
Keyword(s):  
Computational Linguistics ◽  
Language Processing ◽  
Computational Modelling ◽  
Formal Approach ◽  
Future Directions ◽  
Light Verb Constructions ◽  
Light Verb ◽  
Current State ◽  
Linguistic Representations ◽  
Verb Constructions

This chapter introduces the fields of Computational Linguistics (CL)—the computational modelling of linguistic representations and theories—and Natural Language Processing (NLP)—the design and implementation of tools for automated language understanding and production—and discusses some of the existing tensions between the formal approach to linguistics and the current state of the research and development in CL and NLP. The paper goes on to explain the specific challenges faced by CL and NLP for Persian, much of it derived from the intricacies presented by the Perso-Arabic script in automatically identifying word and phrase boundaries in text, as well as difficulties in automatic processing of compound words and light verb constructions. The chapter then provides an overview of the state of the art in current and recent CL and NLP for Persian. It concludes with areas for improvement and suggestions for future directions.

Sign in / Sign up

Export Citation Format

Share Document