Creative and Generative Natural Language Processing and Its Applications

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

Deadline for manuscript submissions: closed (1 August 2022) | Viewed by 12219

Special Issue Editors

Department of Multimedia, Polish-Japanese Academy of Information Technology, 02-008 Warszawa, Poland
Interests: deep learning; machine learning; natural language processing; computational linguistics; multimedia
Special Issues, Collections and Topics in MDPI journals
Wydział Humanistyczny, Jan Dlugosz University in Czestochowa, Waszyngtona 4/8, 42-200 Częstochowa, Poland
Interests: ethics in AI; chatbots; human–chatbot interaction; IE; NER; NLP; ML; MT; corpus linguistics; pluricentrism; specialized language
Special Issues, Collections and Topics in MDPI journals
Faculty of Computer Science, Bialystok University of Technology, Bialystok, Poland
Interests: embedded systems; FPGA; Artificial Intelligence; rough sets

Special Issue Information

Dear Colleagues,

This Special Issue will focus on creative natural language usage and its applications. Whereas others investigate typical areas from the field of NLP, such as parsers, taggers, etc., we will focus our attention on creative and generative research topics not limited to corpora augmentation, creative text generation, natural language understanding, answer generation, dialog agents, etc. We will also focus on its applications in other fields on science and business, especially as far as business costs reductions are concerned. We also invite convergent research articles, particularly if the generally perceived state of the art has not been established yet. We encourage you to submit papers in the areas of (but not limited to): general natural language processing, machine learning, computational and corpora based linguistics, natural language generation and understanding, fake texts detection and generation (e.g., story, poetry, QA answers, chatbot contextual answers, etc.), machine translation and its post-editing, speech technology, ASR automatic transcription and its post editing, summary generation, creative describing, and social signal processing.

Technical Program Committee Members:

1. (PhD Candidate) MSc Karol Chlasta: Polish-Japanese Academy of Information Technology, 02-008 Warsaw; Poland & SWPS University, 03-815 Warsaw, Poland
2. (PhD Candidate) MSc Eng. Emilia Zawadzka-Gosk: Polish-Japanese Academy of Information Technology, 02-008 Warsaw, Poland

Dr. Krzysztof Wołk
Dr. Ida Skubis
Dr. Tomasz Grzes
Guest Editors

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

  • Natural language processing
  • Computational linguistics
  • Corpora language processing
  • Creative text generation
  • Machine translation
  • Automatic post-editing
  • Answer generation methods and applications
  • Corpora augmentation
  • Corpora creation processing and analysis
  • Language generation applications

Published Papers (5 papers)

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

Research

15 pages, 349 KiB  
Article
Study on Using Machine Learning-Driven Classification for Analysis of the Disparities between Categorized Learning Outcomes
Electronics 2022, 11(22), 3652; https://doi.org/10.3390/electronics11223652 - 08 Nov 2022
Cited by 1 | Viewed by 1296
Abstract
Learning outcomes are measurable statements that articulate educational aims in terms of what knowledge, skills, and other competences students possess after successfully completing a given learning experience. This paper presents an analysis of the disparity between the claimed and formulated learning outcomes categorized [...] Read more.
Learning outcomes are measurable statements that articulate educational aims in terms of what knowledge, skills, and other competences students possess after successfully completing a given learning experience. This paper presents an analysis of the disparity between the claimed and formulated learning outcomes categorized in knowledge, skills, and social responsibility competency classes as it is postulated in the European Qualification Framework. We employed machine learning classification algorithms to detect and reveal main errors in their formulation that result in incorrect classification using generally available syllabus data from 22 universities. The proposed method was employed in two stages: preprocessing (creating a Python dataframe structure) and classification (by performing tokenization with the term frequency–inverse document frequency method). The obtained results demonstrated high effectiveness in correct classification for a number of machine learning algorithms. The obtained sensitivity and specificity reached 0.8 for most cases with acceptable positive predictive values for social responsibility competency classes and relatively high negative predictive values greater than 0.8 for all classes. Hence, the presented methodology and results may be a prelude to conducting further studies associated with identifying learning outcomes. Full article
Show Figures

Figure 1

18 pages, 2068 KiB  
Article
Toward Understanding Most of the Context in Document-Level Neural Machine Translation
Electronics 2022, 11(15), 2390; https://doi.org/10.3390/electronics11152390 - 30 Jul 2022
Viewed by 1041
Abstract
Considerable research has been conducted to obtain translations that reflect contextual information in documents and simultaneous interpretations. Most of the existing studies use concatenation data which merge previous and current sentences for training translation models. Although this corpus improves the performance of the [...] Read more.
Considerable research has been conducted to obtain translations that reflect contextual information in documents and simultaneous interpretations. Most of the existing studies use concatenation data which merge previous and current sentences for training translation models. Although this corpus improves the performance of the model, ignoring the contextual correlation between the sentences can disturb translation performance. In this study, we introduce a simple and effective method to capture the contextual correlation of the sentence at the document level of the current sentence, thereby learning an effective contextual representation. In addition, the proposed model structure is applied to a separate residual connection network to minimize the loss of the beneficial influence of incorporating the context. The experimental results show that our methods improve the translation performance in comparison with the state-of-the-art baseline of the Transformer in various translation tasks and two benchmark machine translation tasks. Full article
Show Figures

Figure 1

15 pages, 1981 KiB  
Article
Determining the Intensity of Basic Emotions among People Suffering from Anorexia Nervosa Based on Free Statements about Their Body
Electronics 2022, 11(1), 138; https://doi.org/10.3390/electronics11010138 - 03 Jan 2022
Cited by 2 | Viewed by 1965
Abstract
Objective: This study sought to address one of the challenges of psychiatry-computer aided diagnosis and therapy of anorexia nervosa. The goal of the paper is to present a method of determining the intensity of five emotions (happiness, sadness, anxiety, anger and disgust) in [...] Read more.
Objective: This study sought to address one of the challenges of psychiatry-computer aided diagnosis and therapy of anorexia nervosa. The goal of the paper is to present a method of determining the intensity of five emotions (happiness, sadness, anxiety, anger and disgust) in medical notes, which was then used to analyze the feelings of people suffering from anorexia nervosa. In total, 96 notes were researched (46 from people suffering from anorexia and 52 from healthy people). Method: The developed solution allows a comprehensive assessment of the intensity of five feelings (happiness, sadness, anxiety, anger and disgust) occurring in text notes. This method implements Nencki Affective Word List dictionary extension, in which the original version has a limited vocabulary. The method was tested on a group of patients suffering from anorexia nervosa and a control group (healthy people without an eating disorder). Of the analyzed medical, only 8% of the words are in the original dictionary. Results: As a result of the study, two emotional profiles were obtained: one pattern for a healthy person and one for a person suffering from anorexia nervosa. Comparing the average emotional intensity in profiles of a healthy person and person with a disorder, a higher value of happiness intensity is noticeable in the profile of a healthy person than in the profile of a person with an illness. The opposite situation occurs with other emotions (sadness, anxiety, disgust, anger); they reach higher values in the case of the profile of a person suffering from anorexia nervosa. Discussion: The presented method can be used when observing the patient’s progress during applied therapy. It allows us to state whether the chosen method has a positive effect on the mental state of the patient, and if his emotional profile is similar to the emotional profile of a healthy person. The method can also be used during first diagnosis visit. Full article
Show Figures

Figure 1

15 pages, 525 KiB  
Article
Completing WordNets with Sememe Knowledge
Electronics 2022, 11(1), 79; https://doi.org/10.3390/electronics11010079 - 27 Dec 2021
Cited by 1 | Viewed by 2505
Abstract
WordNets organize words into synonymous word sets, and the connections between words present the semantic relationships between them, which have become an indispensable source for natural language processing (NLP) tasks. With the development and evolution of languages, WordNets need to be constantly updated [...] Read more.
WordNets organize words into synonymous word sets, and the connections between words present the semantic relationships between them, which have become an indispensable source for natural language processing (NLP) tasks. With the development and evolution of languages, WordNets need to be constantly updated manually. To address the problem of inadequate word semantic knowledge of “new words”, this study explores a novel method to automatically update the WordNet knowledge base by incorporating word-embedding techniques with sememe knowledge from HowNet. The model first characterizes the relationships among words and sememes with a graph structure and jointly learns the embedding vectors of words and sememes; finally, it synthesizes word similarities to predict concepts (synonym sets) of new words. To examine the performance of the proposed model, a new dataset connected to sememe knowledge and WordNet is constructed. Experimental results show that the proposed model outperforms the existing baseline models. Full article
Show Figures

Figure 1

23 pages, 847 KiB  
Article
Generation of Cross-Lingual Word Vectors for Low-Resourced Languages Using Deep Learning and Topological Metrics in a Data-Efficient Way
Electronics 2021, 10(12), 1372; https://doi.org/10.3390/electronics10121372 - 08 Jun 2021
Cited by 3 | Viewed by 2806
Abstract
Linguists have been focused on a qualitative comparison of the semantics from different languages. Evaluation of the semantic interpretation among disparate language pairs like English and Tamil is an even more formidable task than for Slavic languages. The concept of word embedding in [...] Read more.
Linguists have been focused on a qualitative comparison of the semantics from different languages. Evaluation of the semantic interpretation among disparate language pairs like English and Tamil is an even more formidable task than for Slavic languages. The concept of word embedding in Natural Language Processing (NLP) has enabled a felicitous opportunity to quantify linguistic semantics. Multi-lingual tasks can be performed by projecting the word embeddings of one language onto the semantic space of the other. This research presents a suite of data-efficient deep learning approaches to deduce the transfer function from the embedding space of English to that of Tamil, deploying three popular embedding algorithms: Word2Vec, GloVe and FastText. A novel evaluation paradigm was devised for the generation of embeddings to assess their effectiveness, using the original embeddings as ground truths. Transferability across other target languages of the proposed model was assessed via pre-trained Word2Vec embeddings from Hindi and Chinese languages. We empirically prove that with a bilingual dictionary of a thousand words and a corresponding small monolingual target (Tamil) corpus, useful embeddings can be generated by transfer learning from a well-trained source (English) embedding. Furthermore, we demonstrate the usability of generated target embeddings in a few NLP use-case tasks, such as text summarization, part-of-speech (POS) tagging, and bilingual dictionary induction (BDI), bearing in mind that those are not the only possible applications. Full article
Show Figures

Figure 1

Back to TopTop