The Missing NLP Paper Guide
The class nobody teaches you: how to write your first paper for ACL, EMNLP, NAACL, EACL, and the rest of the *ACL family.
Why this exists
Your PhD program does not teach you how to write a paper. Your advisor assumes you picked it up by osmosis. Your peers pretend they already know how. The official ACL author guidelines cover the format of a paper: margins, citation style, page limits. They say nothing about the craft. They will not show you how to frame a contribution, or what a related work section needs beyond a list of citations. Nor will they explain why your introduction feels flat, or why a reviewer called your results section "hard to follow" when the numbers are right there.
This guide is that missing class. MIT's Missing Semester of Your CS Education taught students the command line, version control, and debugging tools that nobody had bothered to teach them. We try to do the same for *ACL paper writing, as the methods seminar your program never ran.
Who this is for
- First-time *ACL authors: PhD students, MS students, or industry researchers with a result and a deadline.
- Advisors who want a single artifact to hand new students instead of explaining the same things every cycle.
- Reading groups running a "how to write papers" session.
If you have published five or more first-author *ACL papers, this guide is probably below your level. We would still love your contributions.
What you get
- 31 chapters covering every section of an *ACL paper, plus where to publish, collaboration, figures, rebuttals, reviewing, and what to do after the decision.
- Five examples from real ACL/EMNLP/NAACL papers in each chapter. None are invented.
- A phrasebook of rhetorical moves in each chapter: verbatim openings, pivots, and closings from highly-cited NLP papers. We group them by the job they do (context, gap, proposal, method, result, implication). The idea comes from the Manchester Academic Phrasebook, but our phrases follow *ACL conventions and come from real papers instead of generic academic English.
- A printable one-page submission checklist.
- A
papers-to-read.bibwith every paper cited in Chapter 30, ready to drop into Overleaf. - A structured examples database you can browse by section or by paper.
What this is not
- It is not the official ACL author guidelines. For format, page limits, anonymity rules, and the Responsible NLP Checklist, see the ACL Rolling Review CFP and the ACLPUB formatting page. When the official guidelines and this guide disagree, the official guidelines win.
- It is not AI-generated filler. Every example links to a real paper on the ACL Anthology.
- It is not a substitute for reading great papers. Chapter 30 tells you which ones.
How to use it
Pick the track that matches your situation.
| Your situation | Read these chapters |
|---|---|
| Speed run (deadline in 2 weeks, paper mostly drafted) | 12 Abstract, 13 Introduction, 19 Results, 22 Limitations, 31 Checklist |
| First paper (you have 6–8 weeks) | All chapters, in order |
| First-timer to NLP (deciding where to submit) | 1 Publication Landscape, 2 Understanding the Field, 4 Contribution, 6 Framing, 30 Best Papers |
| Studying the craft (no deadline, want to get better) | 2 Understanding the Field, 4 Contribution, 6 Framing, 30 Best Papers, then any chapter that scratches an itch |
| Reviewing, not writing | 27 How to Review Well, 20 Analysis, 22 Limitations, 30 Best Papers |
Chapters
- The NLP Publication Landscape
- Understanding the Field
- What Kind of Paper Are You Writing?
- What Counts as a Contribution?
- Decoding the Jargon
- Before You Write
- Working With Advisors and Co-authors
- Writing Clearly
- Figures and Tables That Work
- The Structure of an *ACL Paper
- The Title
- The Abstract
- The Introduction
- Related Work
- Background / Preliminaries
- Dataset Construction
- Methods
- Experimental Setup
- Results
- Analysis and Discussion
- Conclusion
- Limitations (Required)
- Ethical Considerations
- Using AI Tools Responsibly
- References & Appendices
- The Rebuttal
- How to Review Well
- After Rejection
- After Acceptance
- Best Papers Worth Reading
- A Final Checklist
Contributing
Yes, please. The guide improves each time an experienced author shares what they have learned. See CONTRIBUTING.md in the repo.
License
CC BY 4.0. Use it, fork it, translate it, hand it to your students. Attribution appreciated.