Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.2
Journals
Symmetry
Special Issues
Symmetry and Asymmetry in Natural Language Processing
share announcement

Symmetry and Asymmetry in Natural Language Processing

A special issue of Symmetry (ISSN 2073-8994). This special issue belongs to the section "Computer".

Deadline for manuscript submissions: 31 October 2026 | Viewed by 3989

Special Issue Editors

Dr. Yang Li

E-Mail Website
Guest Editor
College of Computer and Control Engineering, Northeast Forestry University, Harbin, China
Interests: natural language processing; social media computing; large language models; multimodality
Dr. Junwen Duan

E-Mail Website
Guest Editor
School of Computer Science and Engineering, Central South University, Changsha 410073, China
Interests: information extraction; text mining; knowledge graph
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Natural Language Processing (NLP), as a significant branch of artificial intelligence, is dedicated to enabling computers to understand, generate, and interact with human language. In recent years, NLP has experienced rapid development. Typical NLP tasks include dialogue systems, machine translation, text summarization, information extraction, and topic classification, among others. In these tasks, data and models often exhibit characteristics of symmetry and asymmetry. For example, machine translation generally requires semantic symmetry between the source and target languages, ensuring consistent meaning transmission across different languages. However, it exhibits textual asymmetry due to differences in grammatical structures and expressive methods between languages. Similarly, in text entailment tasks, Siamese network structures typically achieve better performance.

In recent years, with significant advancements in data scale and computational resources, Large Language Models (LLMs) have emerged and demonstrated exceptional performance across numerous NLP tasks, profoundly transforming the research paradigms for NLP tasks, models, and data characterized by symmetry or asymmetry. Therefore, this Special Issue aims to introduce new methods, frameworks, and theories for addressing NLP tasks, data, and models with symmetric and asymmetric characteristics in the context of the era of LLMs.

We are soliciting submissions on a wide range of topics related to NLP (research and review articles), with a particular focus on recent research on NLP tasks with symmetry and asymmetry. Specifically, we welcome submissions including but not limited to the following areas:

  • Solutions for symmetric/asymmetric tasks, models, and data in NLP;
  • New models, algorithms, and frameworks for NLP tasks;
  • Applications of LLMs in NLP tasks;
  • Applications of neural network models in NLP tasks;
  • Research on interpretability and model transparency in NLP;
  • Multimodal tasks in NLP;
  • New tasks and new data reflecting symmetry and asymmetry in NLP.

Dr. Yang Li
Dr. Junwen Duan
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 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-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Symmetry 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 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

  • deep learning
  • natural language processing
  • large language model
  • multimodal model

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.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

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

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

34 pages, 393 KB  
Article
Symmetry-Aware Dual-Encoder Architecture for Context-Aware Grammatical Error Correction in Chinese Learner English: Toward a Spaced-Repetition Instructional Structure Sensitive to Individual Differences
by Jun Tian
Symmetry 2026, 18(4), 579; https://doi.org/10.3390/sym18040579 - 28 Mar 2026
Viewed by 435
Abstract
Grammatical error correction (GEC) for Chinese learner English is still dominated by sentence-level modeling, which limits discourse-level consistency and weakens adaptation to learner-specific error profiles. From an instructional perspective, these limitations also reduce the value of automated feedback as a basis for spaced-repetition [...] Read more.
Grammatical error correction (GEC) for Chinese learner English is still dominated by sentence-level modeling, which limits discourse-level consistency and weakens adaptation to learner-specific error profiles. From an instructional perspective, these limitations also reduce the value of automated feedback as a basis for spaced-repetition instructional structures sensitive to individual differences. This study proposes a symmetry-aware dual-encoder architecture for context-aware GEC in Chinese learner English. A context encoder captures preceding-sentence information, while a source encoder integrates BERT-based semantic representations with Bi-GRU-based syntactic features for the current sentence. A gated decoder performs asymmetric fusion of local and contextual evidence. To better reflect corpus-level tendencies in Chinese learner English, a CLEC-informed augmentation strategy generates synthetic errors using empirical category frequencies as a coarse sampling prior. Experiments on CoNLL-2014, JFLEG, and CLEC show consistent improvements over strong neural baselines in F0.5 and GLEU under the current desktop-oriented implementation setting. Nevertheless, the integration of BERT, dual encoders, and gated decoding introduces non-negligible computational overhead, and the present system is therefore better suited to desktop writing-support scenarios than to strict real-time or large-scale online deployment. The proposed framework thus provides a practical technical basis for personalized grammar feedback and for future spaced-repetition instructional designs in ESL writing support. Full article
(This article belongs to the Special Issue Symmetry and Asymmetry in Natural Language Processing)
25 pages, 1090 KB  
Article
Evaluating Large Language Models on Chinese Zero Anaphora: A Symmetric Winograd-Style Minimal-Pair Benchmark
by Zimeng Li, Yichen Qiao, Xiaoran Chen and Shuangshuang Chen
Symmetry 2026, 18(1), 47; https://doi.org/10.3390/sym18010047 - 26 Dec 2025
Viewed by 908
Abstract
This study investigates how large language models (LLMs) handle Chinese zero anaphora under symmetric minimal-pair conditions designed to neutralize shallow syntactic cues. We construct a Winograd-style benchmark of carefully controlled sentence pairs that require semantic interpretation, pragmatic inference, discourse tracking, and commonsense reasoning [...] Read more.
This study investigates how large language models (LLMs) handle Chinese zero anaphora under symmetric minimal-pair conditions designed to neutralize shallow syntactic cues. We construct a Winograd-style benchmark of carefully controlled sentence pairs that require semantic interpretation, pragmatic inference, discourse tracking, and commonsense reasoning rather than structural heuristics. Using GPT-4, ChatGLM-4, and LLaMA-3 under zero-shot, one-shot, and few-shot prompting, we assess both accuracy and the reasoning traces generated through a standardized Chain-of-Thought diagnostic. Results show that all models perform consistently on items solvable through local cues but display systematic asymmetric errors on 19 universally misinterpreted sentences that demand deeper discourse reasoning. Analysis of these failures reveals weaknesses in semantic role differentiation, topic-chain maintenance, logical-relation interpretation, pragmatic inference, and long-distance dependency tracking. These findings suggest that while LLMs perform well on simpler tasks, they still face challenges in interpreting contextually omitted arguments in Chinese. The study provides a new controlled evaluation resource, an interpretable error analysis framework, and evidence of differences in symmetric versus asymmetric reasoning behaviors in LLMs. Future research could expand the current benchmark to longer discourse contexts, incorporate multi-modal or knowledge-grounded cues, and explore fine-tuning LLMs on discourse data, helping clarify whether asymmetric patterns stem from deeper reasoning challenges or from interactions between models and the evaluation format. Full article
(This article belongs to the Special Issue Symmetry and Asymmetry in Natural Language Processing)
►▼ Show Figures

Figure 1

20 pages, 3728 KB  
Article
Research on Large Language Model-Based Automatic Knowledge Extraction for Coal Mine Equipment Safety
by Ziheng Zhang, Rijia Ding, Yinhang Liu and He Ma
Symmetry 2025, 17(9), 1490; https://doi.org/10.3390/sym17091490 - 9 Sep 2025
Cited by 1 | Viewed by 1626
Abstract
Structured knowledge representation is of great significance for constructing a knowledge graph of coal mine equipment safety. However, traditional methods encounter substantial difficulties when handling the complex semantics and domain-specific terms in technical texts. To tackle this challenge, we propose a knowledge extraction [...] Read more.
Structured knowledge representation is of great significance for constructing a knowledge graph of coal mine equipment safety. However, traditional methods encounter substantial difficulties when handling the complex semantics and domain-specific terms in technical texts. To tackle this challenge, we propose a knowledge extraction framework that integrates large language models (LLMs) with prompt engineering to achieve the efficient joint extraction of information. This framework strengthens the traditional triple structure by introducing symmetric entity-type information encompassing the head entity type and the tail entity type. Furthermore, it enables simultaneous entity recognition and relation extraction within a unified model. Experimental results demonstrate that the proposed knowledge extraction framework significantly outperforms the traditional step-by-step approach of first extracting entities and then relations. To meet the requirements of actual industrial production, we verified the impacts of different prompt strategies, as well as small lightweight models and large complex models, on the extraction task. Through multiple sets of comparative experiments, we found that the Chain-of-Thought (CoT) prompting strategy can effectively improve performance across different models, and the choice of model architecture has a significant impact on task performance. Our research provides an accurate and scalable solution for knowledge graph construction in the coal mine equipment safety domain, and its symmetry-aware design exhibits great potential for cross-domain knowledge transfer. Full article
(This article belongs to the Special Issue Symmetry and Asymmetry in Natural Language Processing)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop