Applied Sciences

Journal Browser

► Journal Browser

Special Issue Editor

Special Issue Information

Dear Colleagues,

Chat GPT and large language models in general have drawn huge attention recently, making natural language processing (NLP) the center of focus in artificial intelligence. At the same time, the expectations of AI as a relatively general aid for people in different tasks have grown considerably.

This Special Issue will publish high-quality, original research papers on various NLP tasks, including, but not limited to, dialogue systems, text summarization, question answering, sentiment analysis, event detection, language generation, language reasoning, and applications of large language models in all possible application areas.

We especially encourage submissions that consider the opportunities and challenges arising from recent trends in NLP research, including, but not limited to, the following:

Combining large language models and algorithms or rule-based systems;
Tuning large language models for different applications;
Multilingual NLP;
Multimodal NLP;
Ethics of NLP.

Prof. Dr. Jyrki Nummenmaa
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. Applied Sciences 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.

Related Special Issue

Published Papers (1 paper)

Research

17 pages, 561 KiB

Open AccessArticle

An Adaptive Contextual Relation Model for Improving Response Generation

by Meiqi Wang, Shiyu Tian, Caixia Yuan and Xiaojie Wang

Appl. Sci. 2024, 14(9), 3941; https://doi.org/10.3390/app14093941 - 6 May 2024

Viewed by 418

Abstract

Context modeling has always been the groundwork for the dialogue response generation task, yet it presents challenges due to the loose context relations among open-domain dialogue sentences. Introducing simulated dialogue futures has been proposed as a solution to mitigate the problem of low history–response relevance. However, these approaches simply assume that the history and future of a dialogue have the same effect on response generation. In reality, the coherence between dialogue sentences varies, and thus, history and the future are not uniformly helpful in response prediction. Consequently, determining and leveraging the relevance between history–response and response–future to aid in response prediction emerges as a pivotal concern. This paper addresses this concern by initially establishing three context relations of response and its context (history and future), reflecting the relevance between the response and preceding and following sentences. Subsequently, we annotate response contextual relation labels on a large-scale dataset, DailyDialog (DD). Leveraging these relation labels, we propose a response generation model that adaptively integrates contributions from preceding and succeeding sentences guided by explicit relation labels. This approach mitigates the impact in cases of lower relevance and amplifies contributions in cases of higher relevance, thus improving the capability of context modeling. Experimental results on public dataset DD demonstrate that our response generation model significantly enhances coherence by 3.02% in long sequences (4-gram) and augments bi-gram diversity by 17.67%, surpassing the performance of previous models. Full article

(This article belongs to the Special Issue New Technologies and Applications of Natural Language Processing (NLP), 2nd Edition)

► Show Figures