New Insights into Neural Network Methods for Natural Language Processing

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (30 June 2022) | Viewed by 2561

Special Issue Editor


E-Mail Website
Guest Editor
Electrical and Electronic Engineering, Near East University, Nicosia, North Cyprus, Mersin 10, Turkey
Interests: learning (artificial intelligence); neural nets; electrochemical electrodes; electrochemical sensors; graphite; potassium compounds; voltammetry (chemical analysis); competitive intelligence; computer vision; convolutional neural nets; diseases; electrochemistry; eye; feature extraction; gaze tracking; image enhancement; iron compounds; medical computing; motion estimation; optimization; pattern classification; reduction (chemical); search engines; semantic web; support vector machines

Special Issue Information

Dear Colleagues,

For more than the last two decades, machine learning has attracted dramatic attention in both academia and industry. Popular deep learning concepts have appeared under the machine learning methods umbrella over the years, dominating many areas of artificial intelligence. Natural language is a challenging object for the computing world to handle.

In recent years, with the aid of developing technologies in computation, big data and new algorithms have been used to propose new solutions and targeting natural language processing (NLP), usually making reference to the fact that NLP has evolved from rule-based methods to statistical approaches. This growing research has led to the success of various NLP methods, such as word embeddings and deep learning methods together.

The aim is for the progress of ongoing research and insights into the lessons learned from current advancements in deep learning and NLP application to lead to more advanced research. We invite a wide range of topics and types of work, including evaluations, methodologies, technological innovation, and design in the area of NLP.

Authors will have an opportunity to present their ongoing work, including research, service, prototype, or products addressing one or more of the suggested topics as presented in the general call for participation. 

Dr. Kamil Dimililer
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Machine learning
  • Deep learning
  • Artificial intelligence
  • Neural networks

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

11 pages, 2019 KiB  
Article
Pre-Training and Fine-Tuning with Next Sentence Prediction for Multimodal Entity Linking
by Lu Li, Qipeng Wang, Baohua Zhao, Xinwei Li, Aihua Zhou and Hanqian Wu
Electronics 2022, 11(14), 2134; https://doi.org/10.3390/electronics11142134 - 7 Jul 2022
Cited by 3 | Viewed by 1769
Abstract
As an emerging research field, more and more researchers are turning their attention to multimodal entity linking (MEL). However, previous works always focus on obtaining joint representations of mentions and entities and then determining the relationship between mentions and entities by these representations. [...] Read more.
As an emerging research field, more and more researchers are turning their attention to multimodal entity linking (MEL). However, previous works always focus on obtaining joint representations of mentions and entities and then determining the relationship between mentions and entities by these representations. This means that their models are often very complex and will result in ignoring the relationship between different modal information from different corpus. To solve the above problems, we proposed a paradigm of pre-training and fine-tuning for MEL. We designed three different categories of NSP tasks for pre-training, i.e., mixed-modal, text-only and multimodal and doubled the amount of data for pre-training by swapping the roles of sentences in NSP. Our experimental results show that our model outperforms other baseline models and our pre-training strategies all contribute to the improvement of the results. In addition, our pre-training gives the final model a strong generalization capability that performs well even on smaller amounts of data. Full article
Show Figures

Figure 1

Back to TopTop