Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Sentence alignment using feed forward neural network.

Mohamed Abdel Fattah1, Fuji Ren, Shingo Kuroiwa

  • 1Faculty of Engineering, University of Tokushima, 2-1 Minamijosanjima, Tokushima, Japan 770-8506. mohafi@is.tokushima-u.ac.jp

International Journal of Neural Systems
|February 8, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

R3DG: Retrieve, Rank, and Reconstruction with Different Granularities for Multimodal Sentiment Analysis.

Research (Washington, D.C.)·2025
Same author

Utterance-Style-Dependent Speaker Verification Using Emotional Embedding with Pretrained Models.

Sensors (Basel, Switzerland)·2025
Same author

Differently Implicational Bandler-Kohout Subproduct Method.

IEEE transactions on cybernetics·2025
Same author

Triple dimensional psychology knowledge encouraging graph attention networks to exploit aspect-based sentiment analysis.

Scientific reports·2025
Same author

Cross-Modal Data Fusion via Vision-Language Model for Crop Disease Recognition.

Sensors (Basel, Switzerland)·2025
Same author

Dense skip-attention for convolutional networks.

Scientific reports·2025
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

This study introduces a novel neural network approach for aligning sentences in parallel corpora, significantly improving accuracy for machine translation and cross-language retrieval tasks. The method achieves a 60% error reduction compared to traditional length-based techniques.

Area of Science:

  • Natural Language Processing
  • Computational Linguistics
  • Machine Learning

Background:

  • Parallel corpora are crucial for multilingual NLP tasks like machine translation.
  • Sentence-aligned corpora offer superior efficiency over non-aligned ones.
  • Existing alignment methods have limitations in accuracy and flexibility.

Purpose of the Study:

  • To develop a novel, accurate, and flexible sentence alignment method for bilingual parallel corpora.
  • To leverage feed-forward neural networks for improved sentence alignment.
  • To reduce errors in cross-language information retrieval and machine translation.

Main Methods:

  • A feed-forward neural network classifier was employed for sentence alignment.
  • Feature parameter vectors, including length, punctuation, and cognate scores, were extracted from text pairs.

Related Experiment Videos

  • The neural network was trained on manually prepared data and tested on separate datasets.

    • Main Results:

    • The proposed neural network approach achieved a 60% error reduction compared to length-based methods on English-Arabic documents.
    • Demonstrated high performance in sentence alignment tasks.
    • Validated the effectiveness across different language pairs.

    Conclusions:

    • The feed-forward neural network classifier offers a significant improvement for sentence alignment in parallel corpora.
    • This approach is adaptable to various language pairs and feature sets, including lexical matching.
    • The method enhances the efficiency and accuracy of downstream NLP applications.