Skip to Content

21 Results Found

  • Article
  • Open Access
24 Citations
8,556 Views
30 Pages

Transformer-Based Re-Ranking Model for Enhancing Contextual and Syntactic Translation in Low-Resource Neural Machine Translation

  • Arifa Javed,
  • Hongying Zan,
  • Orken Mamyrbayev,
  • Muhammad Abdullah and ,
  • Kanwal Ahmed,
  • Dina Oralbekova,
  • Kassymova Dinara and
  • Ainur Akhmediyarova
  • + 3 authors+ 0 author

Neural machine translation (NMT) plays a vital role in modern communication by bridging language barriers and enabling effective information exchange across diverse linguistic communities. Due to the limited availability of data in low-resource langu...

  • Article
  • Open Access
222 Views
32 Pages

10 October 2026

Legal case retrieval requires identifying relevant cases from lengthy judicial documents based on factual and legal similarities. Existing methods often match cases through global semantic representations. When candidates are semantically similar, gl...

(This article belongs to the Special Issue Novel Approaches for Information Retrieval and Exploratory Search)
  • Article
  • Open Access
1 Citations
1,793 Views
24 Pages

12 May 2026

Effective scientific literature retrieval requires moving beyond surface-level term matching toward structured semantic reasoning. This paper presents a controlled empirical study of multi-stage retrieval for scientific literature, integrating lexica...

  • Article
  • Open Access
13 Citations
6,205 Views
13 Pages

26 February 2019

Recent advances in deep neural networks, language modeling and language generation have introduced new ideas to the field of conversational agents. As a result, deep neural models such as sequence-to-sequence, memory networks, and the Transformer hav...

(This article belongs to the Special Issue Artificial Intelligence—Methodology, Systems, and Applications)
  • Article
  • Open Access
52 Views
31 Pages

Vowel-Harmony Constraints in Kazakh ASR: A Systematic Investigation of Integration Approaches

  • Mussa Turdalyuly,
  • Aigerim Yerimbetova,
  • Akbayan Bekarystankyzy,
  • Dina Oralbekova and ,
  • Tolganay Turdalykyzy,
  • Bekturgan Akhmetov,
  • Bakzhan Sakenov,
  • Nazerke Baisholan and
  • Elmira Daiyrbayeva
  • + 4 authors+ 0 author

7 November 2026

Kazakh vowel harmony is well established linguistically, but its explicit integration into modern neural automatic speech recognition (ASR) remains insufficiently studied. This work investigates whether a productive front/back vowel-harmony constrain...

  • Article
  • Open Access
561 Views
23 Pages

Hypersphere-Based Adaptive Filtration for Approximate Nearest Neighbor Search

  • Liefu Ai,
  • Changyu Jiang,
  • Tinglan Hou,
  • Zhengnan Zhu and
  • Jianmin Chen

Existing inverted index-based approximate nearest neighbor search methods are hindered by the necessity for manual adjustment of the quantity of inverted lists and the presence of negative similar results in the candidate set. These limitations inevi...

(This article belongs to the Section Electronic Multimedia)
  • Article
  • Open Access
330 Views
21 Pages

9 September 2026

Part-of-speech (POS) tagging in Arabic is hard because its rich root-and-pattern morphology and the absence of short vowels make one unvoweled string compatible with many categories. This paper presents Jawhar, a hybrid framework that couples a high-...

(This article belongs to the Collection Natural Language Processing and Applications: Challenges and Perspectives)
  • Article
  • Open Access
1,758 Views
26 Pages

31 December 2025

The occurrence of filter bubbles and echo chambers in social media recommendation systems poses a significant threat to information diversity and democratic discourse. Although graph neural networks (GNNs) achieve leading accuracy in user recommendat...

(This article belongs to the Special Issue 2nd Edition of Modern Recommender Systems: Approaches, Challenges and Applications)
  • Article
  • Open Access
30 Citations
10,708 Views
21 Pages

Context-Aware Explainable Recommendation Based on Domain Knowledge Graph

  • Muzamil Hussain Syed,
  • Tran Quoc Bao Huy and
  • Sun-Tae Chung

With the rapid growth of internet data, knowledge graphs (KGs) are considered as efficient form of knowledge representation that captures the semantics of web objects. In recent years, reasoning over KG for various artificial intelligence tasks have...

(This article belongs to the Special Issue Semantic Web Technology and Recommender Systems)
  • Article
  • Open Access

18 November 2026

Business Intelligence systems increasingly rely on complex unstructured evidence, creating a need to retrieve relevant information while presenting it in an accessible form without obscuring decision-relevant content. This study presents a faithfulne...

(This article belongs to the Special Issue Deep Learning for Multimedia Processing and Information Retrieval)
  • Article
  • Open Access
1 Citations
3,778 Views
10 Pages

27 October 2020

Recently, the performance of machine-reading and comprehension (MRC) systems has been significantly enhanced. However, MRC systems require high-performance text retrieval models because text passages containing answer phrases should be prepared in ad...

(This article belongs to the Special Issue Knowledge Retrieval and Reuse)
  • Article
  • Open Access
417 Views
25 Pages

15 September 2026

Group recommender systems must reconcile collective relevance with divergent member preferences. This study introduces Group-Aware Fair and Diverse Decisions (GA-FDD), a transparent decision-layer framework integrating member-derived and direct-group...

(This article belongs to the Special Issue 2nd Edition of Modern Recommender Systems: Approaches, Challenges and Applications)
  • Article
  • Open Access
310 Views
25 Pages

25 September 2026

Reviewing railway construction plans adjacent to operating lines requires distinguishing clause applicability from documentary evidence of obligation fulfillment. This study integrates neural retrieval and auditing with symbolic applicability and evi...

(This article belongs to the Special Issue Advanced Sensing Technologies for Sustainable and Resilient Railway Infrastructures)
  • Article
  • Open Access
1,221 Views
29 Pages

This study proposes a hybrid artificial intelligence (AI) framework for graduate subject allocation that enhances fairness, transparency, and operational efficiency in higher education institutions. Traditional subject allocation processes are predom...

  • Article
  • Open Access
2 Citations
2,805 Views
15 Pages

An Improved Approach for Object Proposals Generation

  • Yao Deng,
  • Huawei Liang and
  • Zhiyan Yi

The objectness measure is a significant and effective method used for generic object detection. However, several object detection methods can achieve accurate results by using more than 1000 candidate object proposals. In addition, the weight of each...

(This article belongs to the Special Issue Deep Learning Based Object Detection II)
  • Article
  • Open Access
7 Citations
2,868 Views
18 Pages

In recent years, Convolutional Neural Network (CNN) models have demonstrated notable advancements in various domains such as image classification and Natural Language Processing (NLP). Despite their success in image classification tasks, their potent...

(This article belongs to the Special Issue Medical Data Processing and Analysis—2nd Edition)
  • Article
  • Open Access
9 Citations
6,326 Views
23 Pages

15 July 2025

Cross-view image matching between UAV and satellite platforms is critical for geographic localization but remains challenging due to domain gaps caused by disparities in imaging sensors, viewpoints, and illumination conditions. To address these chall...

(This article belongs to the Special Issue Temporal and Spatial Analysis of Multi-Source Remote Sensing Images)
  • Article
  • Open Access
4 Citations
3,857 Views
19 Pages

8 September 2023

Pre-trained language model-based neural rankers have been widely applied in information retrieval (IR). However, the robustness issue of current IR models has not received sufficient attention, which could significantly impact the user experience in...

  • Article
  • Open Access
1 Citations
1,544 Views
23 Pages

Deep Relevance Hashing for Remote Sensing Image Retrieval

  • Xiaojie Liu,
  • Xiliang Chen and
  • Guobin Zhu

16 October 2025

With the development of remote sensing technologies, the volume of remote sensing data is growing dramatically, making efficient management and retrieval of large-scale remote sensing images increasingly important. Recently, deep hashing for content-...

(This article belongs to the Section Remote Sensors)
  • Article
  • Open Access
1,492 Views
32 Pages

Analyzing music similarity in large catalogs is challenging because people perceive music differently and important details are found in audio, text, and metadata. This article introduces a multimodal framework that uses an ontology to make music sim...

(This article belongs to the Section Cognitive System)
  • Article
  • Open Access
1 Citations
741 Views
28 Pages

Edge Knowledge in Cognitive Art: Munch Digital Twin

  • Iana Fominska,
  • Gerardo Iovane and
  • Marta Chinnici

26 June 2026

In an era where artificial intelligence is rapidly expanding into creative domains, the challenge of modeling human-like cognition and emotion in generative processes becomes increasingly central. The present study was made in connection with the exh...

(This article belongs to the Special Issue Application of Neural Computation in Artificial Intelligence: 2nd Edition)