Skip to Content

24 Results Found

  • Article
  • Open Access
6 Citations
2,691 Views
20 Pages

2 April 2024

Sentence Boundary Disambiguation (SBD) is crucial for building datasets for tasks such as machine translation, syntactic analysis, and semantic analysis. Currently, most automatic sentence segmentation in Tibetan adopts the methods of rule-based and...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
1 Citations
368 Views
21 Pages

Root, Suffix, or Byte? A Reproducible Study of Sub Word Tokenization for a Morphologically Rich Language (Russian)

  • Mardiyeva Shoxzoda Totliboy Qizi,
  • Shakhlo Djamaldinova and
  • Sabina Umirzakova

17 September 2026

Tokenization is the first design choice in a language model and one of the most frequently overlooked for morphologically rich languages, as it directly shapes sequence length and how related word forms are segmented into reusable sub word units. Usi...

  • Article
  • Open Access
2 Citations
3,516 Views
24 Pages

Neural Architecture Comparison for Bibliographic Reference Segmentation: An Empirical Study

  • Rodrigo Cuéllar Hidalgo,
  • Raúl Pinto Elías,
  • Juan-Manuel Torres-Moreno,
  • Osslan Osiris Vergara Villegas and ,
  • Gerardo Reyes Salgado and
  • Andrea Magadán Salazar
  • + 1 author+ 0 author

18 May 2024

In the realm of digital libraries, efficiently managing and accessing scientific publications necessitates automated bibliographic reference segmentation. This study addresses the challenge of accurately segmenting bibliographic references, a task co...

  • Article
  • Open Access
11 Citations
3,962 Views
13 Pages

A Compression-Based Multiple Subword Segmentation for Neural Machine Translation

  • Keita Nonaka,
  • Kazutaka Yamanouchi,
  • Tomohiro I,
  • Tsuyoshi Okita and ,
  • Kazutaka Shimada and
  • Hiroshi Sakamoto
  • + 1 author+ 0 author

In this study, we propose a simple and effective preprocessing method for subword segmentation based on a data compression algorithm. Compression-based subword segmentation has recently attracted significant attention as a preprocessing method for tr...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
14 Citations
11,483 Views
17 Pages

Comparing Statistical and Neural Machine Translation Performance on Hindi-To-Tamil and English-To-Tamil

  • Akshai Ramesh,
  • Venkatesh Balavadhani Parthasarathy,
  • Rejwanul Haque and
  • Andy Way

2 April 2021

Phrase-based statistical machine translation (PB-SMT) has been the dominant paradigm in machine translation (MT) research for more than two decades. Deep neural MT models have been producing state-of-the-art performance across many translation tasks...

  • Article
  • Open Access
21 Citations
7,909 Views
22 Pages

3 February 2021

Out-of-vocabulary (OOV) words are the most challenging problem in automatic speech recognition (ASR), especially for morphologically rich languages. Most end-to-end speech recognition systems are performed at word and character levels of a language....

(This article belongs to the Special Issue Natural Language Processing for Social Media)
  • Article
  • Open Access
199 Views
42 Pages

29 October 2026

Identity-based multi-proxy signatures (IBMPS) enable an original signer to delegate signing authority to multiple proxy signers, who jointly sign a common message on the original signer’s behalf using their identity-associated private keys. Thi...

(This article belongs to the Section Communications)
  • Article
  • Open Access
775 Views
17 Pages

7 March 2026

RNA N7-methylguanosine (m7G) is an important post-transcriptional epigenetic modification that participates in key biological processes, including RNA processing, stability maintenance, and translational regulation. Medical research has shown that m7...

(This article belongs to the Special Issue Advances and Applications of Machine Learning for Bioinformatics)
  • Article
  • Open Access
420 Views
23 Pages

31 July 2026

Turkic and Uralic languages share almost everything except ancestry: both are agglutinative, both stack long suffix chains onto a stem, both use vowel harmony, and both put the verb last. That coincidence is what makes the pairing worth testing. If a...

(This article belongs to the Collection Natural Language Processing and Applications: Challenges and Perspectives)
  • Article
  • Open Access
5 Citations
2,773 Views
15 Pages

Neural Network-Based Bilingual Lexicon Induction for Indonesian Ethnic Languages

  • Kartika Resiandi,
  • Yohei Murakami and
  • Arbi Haza Nasution

27 July 2023

Indonesia has a variety of ethnic languages, most of which belong to the same language family: the Austronesian languages. Due to the shared language family, words in Indonesian ethnic languages are very similar. However, previous research suggests t...

(This article belongs to the Special Issue Recent Trends in Natural Language Processing and Its Applications)
  • Article
  • Open Access
2 Citations
4,677 Views
18 Pages

A Neural-Network-Based Approach to Chinese–Uyghur Organization Name Translation

  • Aishan Wumaier,
  • Cuiyun Xu,
  • Zaokere Kadeer,
  • Wenqi Liu and ,
  • Yingbo Wang,
  • Xireaili Haierla,
  • Maihemuti Maimaiti,
  • ShengWei Tian and
  • Alimu Saimaiti
  • + 4 authors+ 0 author

21 October 2020

The recognition and translation of organization names (ONs) is challenging due to the complex structures and high variability involved. ONs consist not only of common generic words but also names, rare words, abbreviations and business and industry j...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
14 Citations
5,450 Views
19 Pages

Human Evaluation of English–Irish Transformer-Based NMT

  • Séamus Lankford,
  • Haithem Afli and
  • Andy Way

25 June 2022

In this study, a human evaluation is carried out on how hyperparameter settings impact the quality of Transformer-based Neural Machine Translation (NMT) for the low-resourced English–Irish pair. SentencePiece models using both Byte Pair Encodin...

(This article belongs to the Special Issue Frontiers in Machine Translation)
  • Article
  • Open Access
220 Views
40 Pages

21 October 2026

Chaos-based image encryption schemes are often motivated by the apparent randomness of chaotic sequences and by the nonlinear processing capability of convolutional neural networks (CNNs). However, these properties alone do not guarantee cryptographi...

(This article belongs to the Special Issue Digital Privacy and Security, 3rd Edition)
  • Article
  • Open Access
8 Citations
2,963 Views
24 Pages

ZDBERTa: Advancing Zero-Day Cyberattack Detection in Internet of Vehicle with Zero-Shot Learning

  • Amal Mirza,
  • Sobia Arshad,
  • Muhammad Haroon Yousaf and
  • Muhammad Awais Azam

3 October 2025

The Internet of Vehicles (IoV) is becoming increasingly vulnerable to zero-day (ZD) cyberattacks, which often bypass conventional intrusion detection systems. To mitigate this challenge, this study proposes Zero-Day Bidirectional Encoder Representati...

  • Article
  • Open Access
723 Views
33 Pages

18 April 2026

Knee joint moment is an important biomechanical parameter for sports assessment, rehabilitation monitoring, and human–machine interaction. However, direct measurement is often restricted to laboratory-based settings. Surface electromyography (s...

(This article belongs to the Special Issue Wearable Sensors for Gait, Human Motion Analysis and Health Monitoring: 2nd Edition)
  • Article
  • Open Access
2 Citations
2,797 Views
16 Pages

Map Matching Based on Seq2Seq with Topology Information

  • Yulong Bai,
  • Guolian Li,
  • Tianxiu Lu,
  • Yadong Wu and ,
  • Weihan Zhang and
  • Yidan Feng
  • + 1 author+ 0 author

2 December 2023

Most existing road network matching algorithms are designed based on previous rules and do not fully utilize the potential of big data and historical tracks. To solve this problem, we introduce a new road network matching algorithm based on deep lear...

  • Article
  • Open Access
3 Citations
3,470 Views
17 Pages

5 August 2021

In this paper, we inspect the theoretical problem of counting the number of analogies between sentences contained in a text. Based on this, we measure the analogical density of the text. We focus on analogy at the sentence level, based on the level o...

(This article belongs to the Special Issue Novel Methods and Applications in Natural Language Processing)
  • Article
  • Open Access
17 Citations
9,461 Views
15 Pages

A Mixed Malay–English Language COVID-19 Twitter Dataset: A Sentiment Analysis

  • Jeffery T. H. Kong,
  • Filbert H. Juwono,
  • Ik Ying Ngu,
  • I. Gde Dharma Nugraha and ,
  • Yan Maraden and
  • W. K. Wong
  • + 1 author+ 0 author

Social media has evolved into a platform for the dissemination of information, including fake news. There is a lot of false information about the current situation of the Coronavirus Disease 2019 (COVID-19) pandemic, such as false information regardi...

(This article belongs to the Topic Social Computing and Social Network Analysis)
  • Article
  • Open Access
195 Views
26 Pages

Hypernetwork-Based Spectral BRDF Reconstruction from Sparse RGB and Spectral Measurements

  • Roman Rodionov,
  • Egor Prikhodko,
  • Vadim Sanzharov,
  • Nikolay Mayorov and
  • Alexey Voloboy

14 November 2026

The optical properties of materials are essential for computer-based lighting simulation and computer vision tasks. They are commonly described by a bidirectional reflectance distribution function (BRDF). This paper proposes a hypernetwork-based arch...

(This article belongs to the Special Issue Deep Learning Technologies and Their Applications in Image Processing, Computer Vision, and Computational Intelligence)
  • Article
  • Open Access
5 Citations
4,450 Views
15 Pages

1 July 2024

In current software applications, numerous vulnerabilities may be present. Attackers attempt to exploit these vulnerabilities, leading to security breaches, unauthorized entry, data theft, or the incapacitation of computer systems. Instead of address...

(This article belongs to the Special Issue Cyber Security and Software Engineering)
  • Article
  • Open Access
14 Citations
5,024 Views
20 Pages

Dynamic Acoustic Unit Augmentation with BPE-Dropout for Low-Resource End-to-End Speech Recognition

  • Aleksandr Laptev,
  • Andrei Andrusenko,
  • Ivan Podluzhny,
  • Anton Mitrofanov and ,
  • Ivan Medennikov and
  • Yuri Matveev
  • + 1 author+ 0 author

28 April 2021

With the rapid development of speech assistants, adapting server-intended automatic speech recognition (ASR) solutions to a direct device has become crucial. For on-device speech recognition tasks, researchers and industry prefer end-to-end ASR syste...

(This article belongs to the Special Issue Human-Computer Interaction in Smart Environments)
  • Article
  • Open Access
13 Citations
3,014 Views
21 Pages

14 October 2023

Using traditional methods based on detection rules written by human security experts presents significant challenges for the accurate detection of network threats, which are becoming increasingly sophisticated. In order to deal with the limitations o...

(This article belongs to the Special Issue AI in Cybersecurity, 2nd Edition)
  • Article
  • Open Access
1 Citations
1,701 Views
38 Pages

Tongan Speech Recognition Based on Layer-Wise Fine-Tuning Transfer Learning and Lexicon Parameter Enhancement

  • Junhao Geng,
  • Dongyao Jia,
  • Ziqi Li,
  • Zihao He and ,
  • Nengkai Wu,
  • Weijia Zhang and
  • Rongtao Cui
  • + 2 authors+ 0 author

24 October 2025

Speech recognition, as a key driver of artificial intelligence and global communication, has advanced rapidly in major languages, while studies on low-resource languages remain limited. Tongan, a representative Polynesian language, carries significan...

(This article belongs to the Special Issue Techniques and Applications of Natural Language Processing)
  • Article
  • Open Access
1 Citations
1,365 Views
22 Pages

14 February 2026

Neural machine translation (NMT) performance is strongly influenced by tokenization strategies, particularly for morphologically rich languages such as Arabic. Despite the importance of tokenization, there is a lack of controlled, reproducible studie...

(This article belongs to the Special Issue Human and Machine Translation: Recent Trends and Foundations)