High-resource Language-specific Training for Multilingual Neural Machine Translation

Yang, Jian; Yin, Yuwei; Ma, Shuming; Zhang, Dongdong; Li, Zhoujun; Wei, Furu

doi:10.24963/ijcai.2022/619

Cited by 9 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sentence-level Machine Translation Sentence-level neural machine translation has developed immensely in the past few years, from RNN-based [26,2,34,35,8,38], CNN-based [7], to the self-attention-based architecture [28,33,25,39,41,40,37,36]. However, these models always performed in a sentence-by-sentence manner, ignoring the long-distance dependencies.…”

Section: Related Workmentioning

confidence: 99%

HanoiT: Enhancing Context-aware Translation via Selective Context

Yang¹,

Yin²,

Ma³

et al. 2023

Preprint

View full text Add to dashboard Cite

Context-aware neural machine translation aims to use the document-level context to improve translation quality. However, not all words in the context are helpful. The irrelevant or trivial words may bring some noise and distract the model from learning the relationship between the current sentence and auxiliary context. To mitigate this problem, we propose a novel end-to-end encoder-decoder model with a layer-wise selection mechanism to sift and refine the long document context. To verify the effectiveness of our method, extensive experiments and extra quantitative analysis are conducted on four document-level machine translation benchmarks. The experimental results demonstrate that our model significantly outperforms previous models on all datasets via the soft selection mechanism.

show abstract

Section: Related Workmentioning

confidence: 99%

HanoiT: Enhancing Context-aware Translation via Selective Context

Yang¹,

Yin²,

Ma³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Real-time translation pipelines [2] now include OCR [13][14][15] as one of their central pillars, which helps solve all translation and interpretation problems. Our research results with the technological pipeline (see Figure 1)-supporting the collaborative videoconferencing tools and platforms-can be applied to healthcare and sports safety.…”

Section: Introductionmentioning

confidence: 99%

Synthetized Multilanguage OCR Using CRNN and SVTR Models for Realtime Collaborative Tools

et al. 2023

View full text Add to dashboard Cite

Background: Remote diagnosis using collaborative tools have led to multilingual joint working sessions in various domains, including comprehensive health care, and resulting in more inclusive health care services. One of the main challenges is providing a real-time solution for shared documents and presentations on display to improve the efficacy of noninvasive, safe, and far-reaching collaborative models. Classic optical character recognition (OCR) solutions fail when there is a mixture of languages or dialects or in case of the participation of different technical levels and skills. Due to the risk of misunderstandings caused by mistranslations or lack of domain knowledge of the interpreters involved, the technological pipeline also needs artificial intelligence (AI)-supported improvements on the OCR side. This study examines the feasibility of machine learning-supported OCR in a multilingual environment. The novelty of our method is that it provides a solution not only for different speaking languages but also for a mixture of technological languages, using artificially created vocabulary and a custom training data generation approach. Methods: A novel hybrid language vocabulary creation method is utilized in the OCR training process in combination with convolutional recurrent neural networks (CRNNs) and a single visual model for scene text recognition within the patch-wise image tokenization framework (SVTR). Data: In the research, we used a dedicated Python-based data generator built on dedicated collaborative tool-based templates to cover and simulated the real-life variances of remote diagnosis and co-working collaborative sessions with high accuracy. The generated training datasets ranged from 66 k to 8.5 M in size. Twenty-one research results were analyzed. Instruments: Training was conducted by using tuned PaddleOCR with CRNN and SVTR modeling and a domain-specific, customized vocabulary. The Weight & Biases (WANDB) machine learning (ML) platform is used for experiment tracking, dataset versioning, and model evaluation. Based on the evaluations, the training dataset was adjusted by using a different language corpus or/and modifications applied to templates. Results: The machine learning models recognized the multilanguage/hybrid texts with high accuracy. The highest precision scores achieved are 90.25%, 91.35%, and 93.89%. Conclusions: machine learning models for special multilanguages, including languages with artificially made vocabulary, perform consistently with high accuracy.

show abstract

“…Although the backdoor attack has been extensively researched in multiple applications, such as computer vision (CV) [11][12][13][14][15][16][17] and natural language processing (NLP) [18][19][20][21][22][23][24][25][26][27][28][29], there is no research in the field of DGA detection. Due to the particularity of DGA , existing backdoor attacks can not be directly applied to the DGA detection approach based on deep learning.…”

Section: Introductionmentioning

confidence: 99%

BadDGA: Backdoor Attack on LSTM-Based Domain Generation Algorithm Detector

Zhai

Yang

et al. 2023

Electronics

Self Cite

View full text Add to dashboard Cite

Due to the outstanding performance of deep neural networks (DNNs), many researchers have begun to transfer deep learning techniques to their fields. To detect algorithmically generated domains (AGDs) generated by domain generation algorithm (DGA) in botnets, a long short-term memory (LSTM)-based DGA detector has achieved excellent performance. However, the previous DNNs have found various inherent vulnerabilities, so cyberattackers can use these drawbacks to deceive DNNs, misleading DNNs into making wrong decisions. Backdoor attack as one of the popular attack strategies strike against DNNs has attracted widespread attention in recent years. In this paper, to cheat the LSTM-based DGA detector, we propose BadDGA, a backdoor attack against the LSTM-based DGA detector. Specifically, we offer four backdoor attack trigger construction methods: TLD-triggers, Ngram-triggers, Word-triggers, and IDN-triggers. Finally, we evaluate BadDGA on ten popular DGA datasets. The experimental results show that under the premise of 1‰ poisoning rate, our proposed backdoor attack can achieve a 100% attack success rate to verify the effectiveness of our method. Meanwhile, the model’s utility on clean data is influenced slightly.

show abstract

High-resource Language-specific Training for Multilingual Neural Machine Translation

Cited by 9 publications

References 2 publications

HanoiT: Enhancing Context-aware Translation via Selective Context

HanoiT: Enhancing Context-aware Translation via Selective Context

Synthetized Multilanguage OCR Using CRNN and SVTR Models for Realtime Collaborative Tools

BadDGA: Backdoor Attack on LSTM-Based Domain Generation Algorithm Detector

Contact Info

Product

Resources

About