Paper Submission Guidelines
Paper Structure: Maximum 4 pages (excluding unlimited references).
1. Abstract
Brief summary of your paper in a few sentences.
2. Introduction
- Task description and importance; mention language(s) covered; cite task overview paper
- Your main system strategy
- Key findings, ranking, challenges discovered; include code URL if available (Highly recommended)
3. Background
- Summarize task setup: input/output types (with examples)
- Dataset details: language, genre, size
- Tracks participated in (if applicable)
- Cite relevant related work showing your contribution's novelty
4. System Overview
- Key algorithms and design decisions
- Resources used beyond provided training data
- How you addressed task challenges
- Include equations/pseudocode for novel approaches
- Provide concrete algorithm examples
- For multiple systems, clearly distinguish each configuration
5. Experimental Setup
- Data split usage (train/dev/test)
- Preprocessing and hyperparameter details for replication
- External tools/libraries (with versions and URLs)
- Task evaluation metrics summary
- Put detailed implementation in Appendix if space-limited
6. Results
- Quantitative findings: Official metrics performance and ranking
- Analysis: Ablations, comparisons, design decisions impact
- Error analysis: System mistakes, confusion matrices, error types, make sure
to provide some examples
- Clearly mark which data split used for each analysis
- Distinguish official vs. post-submission results
7. Conclusion
Summary of system, limitations, results, and future work directions.
8. Acknowledgments
Thank contributors, grants, anonymous reviewers.
9. Appendix
Low-level details for replication that aren't essential for understanding main concepts.
Formatting Requirements
Templates and Style
- Must use: Official EMNLP 2025 (ACL) style templates (LaTeX or Word)
- Download from: https://github.com/acl-org/ACLPUB
- Follow: General "ACL" conference formatting guidelines
- Do NOT: Modify style files or use templates from other conferences to avoid the
paper rejection
Consequences
- Non-conforming submissions (wrong paper size, margins, font size) will be rejected
without review.
Key Principles
Focus on:
- Replicability: Provide all necessary implementation details
- Analysis: Emphasize results over rankings; include multiple runs and ablations
- Clarity: Brief task outline (avoid duplicating task paper); use placeholder
citations initially
Required elements:
- Cite task overview paper
- Follow EMNLP templates exactly
- Use title format:
<Team Name> at <Task Name>: <Your Contribution>
For popular algorithms: Citation suffices (no
need for full mathematical details)
Space management: Move detailed
parameters/hyperparameters to Appendix if needed