Deep Learning and Natural Language Processing II

A special issue of Future Internet (ISSN 1999-5903). This special issue belongs to the section "Big Data and Augmented Intelligence".

Deadline for manuscript submissions: 20 September 2024 | Viewed by 8756

Special Issue Editor


E-Mail Website
Guest Editor
Algoritmi Research Center, Informatics Department, University of Évora, 7002–554 Évora, Portugal
Interests: artificial intelligence; natural language processing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Over the last years, natural language processing tasks have been able to improve their performance significantly through the use of deep learning methodologies. Machine translation, summarization, and question-answering systems are just some examples of tasks that science has been able to elevate to reach a high level of performance.

In this Special Issue, we welcome new research contributions and survey papers describing advances in this relevant domain. Potential topics include:

  • Deep learning architectures specialized for NLP;
  • Deep learning based approaches to NLP tasks, such as, NERC, syntactic parsers, semantic analysis, semantic role labeling, information extraction, sentiment analysis, summarization, question-answering and machine translation;
  • Hybrid (symbolic + deep learning) approaches to NLP;
  • Text annotation using deep-learning approaches;
  • Survey papers;
  • Generative models, such as GPT-3.

Dr. Paulo Quaresma
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. Future Internet is an international peer-reviewed open access monthly 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 1600 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

  • deep learning
  • natural language processing

Related Special Issue

Published Papers (4 papers)

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

Research

Jump to: Review

20 pages, 19399 KiB  
Article
Speech Inpainting Based on Multi-Layer Long Short-Term Memory Networks
by Haohan Shi, Xiyu Shi and Safak Dogan
Future Internet 2024, 16(2), 63; https://doi.org/10.3390/fi16020063 - 17 Feb 2024
Cited by 1 | Viewed by 1126
Abstract
Audio inpainting plays an important role in addressing incomplete, damaged, or missing audio signals, contributing to improved quality of service and overall user experience in multimedia communications over the Internet and mobile networks. This paper presents an innovative solution for speech inpainting using [...] Read more.
Audio inpainting plays an important role in addressing incomplete, damaged, or missing audio signals, contributing to improved quality of service and overall user experience in multimedia communications over the Internet and mobile networks. This paper presents an innovative solution for speech inpainting using Long Short-Term Memory (LSTM) networks, i.e., a restoring task where the missing parts of speech signals are recovered from the previous information in the time domain. The lost or corrupted speech signals are also referred to as gaps. We regard the speech inpainting task as a time-series prediction problem in this research work. To address this problem, we designed multi-layer LSTM networks and trained them on different speech datasets. Our study aims to investigate the inpainting performance of the proposed models on different datasets and with varying LSTM layers and explore the effect of multi-layer LSTM networks on the prediction of speech samples in terms of perceived audio quality. The inpainted speech quality is evaluated through the Mean Opinion Score (MOS) and a frequency analysis of the spectrogram. Our proposed multi-layer LSTM models are able to restore up to 1 s of gaps with high perceptual audio quality using the features captured from the time domain only. Specifically, for gap lengths under 500 ms, the MOS can reach up to 3~4, and for gap lengths ranging between 500 ms and 1 s, the MOS can reach up to 2~3. In the time domain, the proposed models can proficiently restore the envelope and trend of lost speech signals. In the frequency domain, the proposed models can restore spectrogram blocks with higher similarity to the original signals at frequencies less than 2.0 kHz and comparatively lower similarity at frequencies in the range of 2.0 kHz~8.0 kHz. Full article
(This article belongs to the Special Issue Deep Learning and Natural Language Processing II)
Show Figures

Figure 1

16 pages, 515 KiB  
Article
Domain Adaptation Speech-to-Text for Low-Resource European Portuguese Using Deep Learning
by Eduardo Medeiros, Leonel Corado, Luís Rato, Paulo Quaresma and Pedro Salgueiro
Future Internet 2023, 15(5), 159; https://doi.org/10.3390/fi15050159 - 24 Apr 2023
Cited by 1 | Viewed by 1495
Abstract
Automatic speech recognition (ASR), commonly known as speech-to-text, is the process of transcribing audio recordings into text, i.e., transforming speech into the respective sequence of words. This paper presents a deep learning ASR system optimization and evaluation for the European Portuguese language. We [...] Read more.
Automatic speech recognition (ASR), commonly known as speech-to-text, is the process of transcribing audio recordings into text, i.e., transforming speech into the respective sequence of words. This paper presents a deep learning ASR system optimization and evaluation for the European Portuguese language. We present a pipeline composed of several stages for data acquisition, analysis, pre-processing, model creation, and evaluation. A transfer learning approach is proposed considering an English language-optimized model as starting point; a target composed of European Portuguese; and the contribution to the transfer process by a source from a different domain consisting of a multiple-variant Portuguese language dataset, essentially composed of Brazilian Portuguese. A domain adaptation was investigated between European Portuguese and mixed (mostly Brazilian) Portuguese. The proposed optimization evaluation used the NVIDIA NeMo framework implementing the QuartzNet15×5 architecture based on 1D time-channel separable convolutions. Following this transfer learning data-centric approach, the model was optimized, achieving a state-of-the-art word error rate (WER) of 0.0503. Full article
(This article belongs to the Special Issue Deep Learning and Natural Language Processing II)
Show Figures

Figure 1

26 pages, 709 KiB  
Article
Creation, Analysis and Evaluation of AnnoMI, a Dataset of Expert-Annotated Counselling Dialogues
by Zixiu Wu, Simone Balloccu, Vivek Kumar, Rim Helaoui, Diego Reforgiato Recupero and Daniele Riboni
Future Internet 2023, 15(3), 110; https://doi.org/10.3390/fi15030110 - 14 Mar 2023
Cited by 5 | Viewed by 2521
Abstract
Research on the analysis of counselling conversations through natural language processing methods has seen remarkable growth in recent years. However, the potential of this field is still greatly limited by the lack of access to publicly available therapy dialogues, especially those with expert [...] Read more.
Research on the analysis of counselling conversations through natural language processing methods has seen remarkable growth in recent years. However, the potential of this field is still greatly limited by the lack of access to publicly available therapy dialogues, especially those with expert annotations, but it has been alleviated thanks to the recent release of AnnoMI, the first publicly and freely available conversation dataset of 133 faithfully transcribed and expert-annotated demonstrations of high- and low-quality motivational interviewing (MI)—an effective therapy strategy that evokes client motivation for positive change. In this work, we introduce new expert-annotated utterance attributes to AnnoMI and describe the entire data collection process in more detail, including dialogue source selection, transcription, annotation, and post-processing. Based on the expert annotations on key MI aspects, we carry out thorough analyses of AnnoMI with respect to counselling-related properties on the utterance, conversation, and corpus levels. Furthermore, we introduce utterance-level prediction tasks with potential real-world impacts and build baseline models. Finally, we examine the performance of the models on dialogues of different topics and probe the generalisability of the models to unseen topics. Full article
(This article belongs to the Special Issue Deep Learning and Natural Language Processing II)
Show Figures

Figure 1

Review

Jump to: Research

28 pages, 669 KiB  
Review
Methods of Annotating and Identifying Metaphors in the Field of Natural Language Processing
by Martina Ptiček and Jasminka Dobša
Future Internet 2023, 15(6), 201; https://doi.org/10.3390/fi15060201 - 31 May 2023
Cited by 1 | Viewed by 2667
Abstract
Metaphors are an integral and important part of human communication and greatly impact the way our thinking is formed and how we understand the world. The theory of the conceptual metaphor has shifted the focus of research from words to thinking, and also [...] Read more.
Metaphors are an integral and important part of human communication and greatly impact the way our thinking is formed and how we understand the world. The theory of the conceptual metaphor has shifted the focus of research from words to thinking, and also influenced research of the linguistic metaphor, which deals with the issue of how metaphors are expressed in language or speech. With the development of natural language processing over the past few decades, new methods and approaches to metaphor identification have been developed. The aim of the paper is to map the methods of annotating and identifying metaphors in the field of natural language processing and to give a systematic overview of how relevant linguistic theories and natural language processing intersect. The paper provides an outline of cognitive linguistic metaphor theory and an overview of relevant methods of annotating linguistic and conceptual metaphors as well as publicly available datasets. Identification methods are presented chronologically, from early approaches and hand-coded knowledge to statistical methods of machine learning and contemporary methods of using neural networks and contextual word embeddings. Full article
(This article belongs to the Special Issue Deep Learning and Natural Language Processing II)
Show Figures

Figure 1

Back to TopTop