This Second workshop of NeusymBridge @COLING 2025(Bridging Neurons and Symbols for NLP and Knowledge Graph Reasoning, abbreviated as NeusymBridge below) focuses on the integration of symbolic knowledge and neural models to address challenges in natural language processing (NLP) and knowledge reasoning. The workshop brings together researchers from both academia and industry to explore cutting-edge approaches in neurosymbolic systems, aiming to enhance large language models (LLMs) with more robust reasoning and knowledge representation capabilities. Key topics include the use of knowledge graphs, symbolic inference, and hybrid models to improve the interpretability and reliability of LLMs.

NeusymBridge Workshop @COLING 2025 (abbreviated as NeusymBridge below) invites the submission of long and short papers featuring substantial, original, and unpublished research on Natural Language Processing and Knowledge Graph reasoning.

Paper Submission Information

NeusymBridge Workshop @COLING 2025 (abbreviated as NeusymBridge below) invites the submission of long papers of up to eight pages and short papers of up to four pages. These page limits only apply to the main body of the paper. At the end of the paper (after the conclusions but before the references) papers need to include a mandatory section discussing the limitations of the work and, optionally, a section discussing ethical considerations. Papers can include unlimited pages of references and an unlimited appendix. Authors should follow the general instructions for COLING 2025 proceedings, which are an adaptation of the general instructions for \*ACL proceedings.

Please use the template provided by COLING 2025 using the following link: COLING 2025 PAPER TYPES AND FORMATS.

Paper Submission Site

Papers should be submitted through Softconf/START using the following link: Softconf.

Each paper will receive a minimum of three reviews. Authors will have the opportunity to provide a short rebuttal to clarify any misunderstandings. The review process will be double-blind. Reviewers will not see authors, authors will not see reviewers. Reviews and submissions will not be made publicly visible.

Submission Topics

The workshop invites submissions on a wide range of topics, including but not limited to:

  • Proposing novel knowledge representations that are derived from transdisciplinary research
  • Using knowledge graphs or other types of symbolic Knowledge to improve the quality of LLMs
  • Neuro-symbolic parsing methods for NLP
  • Using symbolic structures, or natural languages, to interpret the reasoning mechanism of pre-trained language models
  • Exploring the reasoning mechanism of LLMs
  • Distilling symbolic knowledge from LLMs
  • Proposing benchmark datasets and evaluation matrices for neuro-symbolic approaches to NLP tasks
  • Proposing novel NLP tasks for neuro-symbolic approaches
  • NLP applications in classification, sense-disambiguation, sentiment analysis, question-answering, knowledge graph reasoning
  • Critical analysis of traditional deep learning or LLMs
  • Analysing spatial reasoning of LLMs
  • Proposing novel neural computing that may reach symbolic-level reasoning
  • Proposing benchmark datasets and matrices to evaluate the gap between neural reasoning and symbolic reasoning
  • Addressing efficiency issues in neuro-symbolic systems
  • Identifying challenges and opportunities of neuro-symbolic systems
  • Developing retrieval augmented models for combining KG and LLMs
  • Applying neuro-symbolic approaches to humor generation and other real-life applications
  • Datasets and evaluation matrices supporting both neural and symbolic approaches to NLP tasks
  • New meaning representation for with both symbolic and neural meaning representation
  • New neural architecture for both heuristic reasoning with data and rational reasoning with symbolic rules
  • Innovative applications of hybrid models combining symbolic and neural architectures

Important Dates

All deadlines are 11:59PM UTC-12:00 (“anywhere on Earth”)
Submission Deadline:November 10, 2024December 1, 2024
Notification of Acceptance:December 5, 2024December 6, 2024
Camera-Ready papers due:December 13, 2024
Workshop Day: January 20, 2025

Note

When submitting a paper from the START page, please provide essential information about resources (in a broad sense, i.e. also technologies, standards, evaluation kits, etc.) that have been used for the work described in the paper or are a new result of your research. Moreover, ELRA encourages all LREC-COLING authors to share the described LRs (data, tools, services, etc.) to enable their reuse and replicability of experiments (including evaluation ones).

Contact Information

Workshop Chairs

  • Kang Liu, Institute of Automation, Chinese Academy of Sciences, China
  • Yangqiu Song, The Hong Kong University of Science and Technology, China
  • Zhen Han, Amazon Inc., United States
  • Rafet Sifa, University of Bonn, Germany
  • Shizhu He, Institute of Automation, Chinese Academy of Sciences, China
  • Yunfei Long, University of Essex, United Kingdom

For questions about submission, please contact: shizhu.he@nlpr.ia.ac.cn