Natural Language Processing (NLP) with Applications and Natural Language Understanding (NLU)

Dear Colleagues,

NLP is both a technology and a science, a branch of computational linguistics and artificial intelligence. The current LLM hype has maybe reached a peak thanks to CHATGPT and its attractive applications: how will this influence NLP, and is NLP still needed, maybe in a different form? This Special Issue aims to bring together researchers in all areas of NLP to discuss applications and future research directions in the field of natural language understanding for DNNs.

NLP applications are all based on the same source of knowledge, i.e., words, as even visual neural networks need words for their captions. LLM vocabularies are usually made up of the first most frequent 50,000 words or types extracted from billions of tokens, but they still produce hallucinations and biases. Part of the problem at the heart of DNN use is their lack of generalization and their inherent inability to understand what they are processing.

In this Special Issue, we wish to feature papers on all kinds of applications that are language-oriented, starting from speech recognition and synthesis, machine translation, and question answering. Below is a provisional list of the most relevant ones:

• Sentiment Analysis from Social Media
• Chatbots and Smart Assistants
• Email Filters
• Text Summarization
• Customer Support and Analytics for Market Intelligence
• Online Search Engine and Autocomplete
• Recruitment and Hiring
• Auto-Correct and Next-Word Prediction
• Spell and Grammar Checking
• Text Extraction and Classification
• Image and Facial Recognition for/from Captions
• NLP for Multimedia Self-Learning Language Tools

Traditionally, NLP techniques vary from symbolic to statistical approaches but always address linguistic content that may be constituted by phonemes or phones, morphemes or sequences of subword units, tokens of various types and length, including punctuation, words, multiwords, or polywords, syntactic constituents, and dependency structures. These low-level strata make up what is currently addressed directly or indirectly by the majority of applications.

Attempts are being made to address text understanding, which belongs to higher levels of linguistic knowledge: pronominal binding, coreference resolution, quantifier raising, semantic representation in terms of AMRs, or other similar theories completed by word-sense disambiguation. Not all of these tasks are suited to current transformer-based LLMs, but they could be carried out by NLP components. Finally, we assume that, to attain reasoning which includes causal inference from knowledge of the world, lower linguistic strata should not be erased but used as a trigger for further processing. Thus, we wish to dedicate a separate subsection of this Special Issue to these latter topics, which may be dubbed as NLP for future applications with AI for text understanding or NLU, promoting project presentation and works in progress.

In sum, in this Special Issue, we wish to bring together researchers by discussing innovative applications in all fields of NLP, alongside innovative result in semantic processing for NLU.

Prof. Dr. Rodolfo Delmonte
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 250 words) can be sent to the Editorial Office for assessment.

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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information 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 1800 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.