Simple Science

Cutting edge science explained simply

# Computer Science# Computation and Language

Essential Formatting Guidelines for AAAI Press Papers

Follow these guidelines to format your paper for AAAI Press submission.

― 3 min read


AAAI Press PaperAAAI Press PaperGuidelinessuccessful submission.Format your paper correctly for
Table of Contents

Formatting Your Paper for AAAI Press

Introduction

If you have a paper accepted for an AAAI Press proceeding, there are guidelines you need to follow to ensure your paper looks the same as others. This document lays out the steps for formatting your work properly.

Basic Requirements

Before you start, make sure you are using the correct style files for your paper. These files help maintain a uniform look across all accepted papers. You must read and follow these instructions carefully.

Preparing Your Paper

When preparing your paper:

  • Use the AAAI style file for formatting.
  • Make sure to submit both your paper in PDF format and the source document.
  • Keep in mind the deadlines for submission and any fees that may apply.

General Formatting Instructions

  1. File Format: Your paper should be in PDF format. Make sure to compile using a system that supports PDF.
  2. Fonts and Size: Use Times or Nimbus fonts. The standard font size is 10 points with 12 points for leading.
  3. Margins and Paper Size: You must use US letter size (8.5 by 11 inches) with specific margin sizes:
    • Top: 0.75 inches
    • Left: 0.75 inches
    • Right: 0.75 inches
    • Bottom: 1.25 inches
  4. Two-Column Format: Your paper should be formatted in two columns that are 3.3 inches wide with a space of 0.375 inches between them.

Titles and Authors

  • Title: The title should be centered and in 16-point bold font.
  • Author Information: Names should be centered below the title, in 12-point font. Include affiliations in 9-point font.

Sections and Headings

  • Use clear headings to define sections of your paper.
  • You're allowed to use section numbers, but it's not necessary for shorter papers.
  • Each section should flow into the next without unnecessary breaks.

Abstract and Keywords

  • Start with a brief abstract that summarizes the main points of your paper.
  • Avoid including Citations in your abstract.

References

  • List references at the end. Follow consistent formatting for citations.
  • Use a bibliography style compatible with the AAAI format.

Figures and Tables

  • Place figures and tables in the paper where they are first mentioned.
  • Ensure all figures are high-resolution (300 dpi is recommended).
  • Use appropriate file formats such as JPG, PNG, or PDF for figures.

Including Graphics

  • Graphics must not have any commands that alter their size or margins once included.
  • Use commands that ensure all fonts in graphics are embedded.

Footnotes and Citations

  • Use footnotes sparingly. If necessary, they should appear at the bottom of the page.
  • Citations must include the author's name and the year, formatted properly.

Technical Requirements

  • No Page Numbers: Do not include page numbers, footers, or headers in your submission.
  • File Size: Keep your final submission under 10 MB.
  • No Obsolete Files: Make sure you are not using any old version of the style files.

Submission Process

  1. Prepare all necessary files and ensure they are in the correct format.
  2. Submit files by the deadline outlined by AAAI.
  3. Use the provided electronic submission form.

Proofreading Your Document

Make sure to review your document thoroughly. Look for:

  • Formatting errors,
  • Missing information,
  • Proper citation styles.

Conclusion

Following these guidelines will help ensure your paper is accepted without issues. Review all steps carefully and submit your work on time. Thank you for contributing to AAAI Press.

Original Source

Title: Not Enough Labeled Data? Just Add Semantics: A Data-Efficient Method for Inferring Online Health Texts

Abstract: User-generated texts available on the web and social platforms are often long and semantically challenging, making them difficult to annotate. Obtaining human annotation becomes increasingly difficult as problem domains become more specialized. For example, many health NLP problems require domain experts to be a part of the annotation pipeline. Thus, it is crucial that we develop low-resource NLP solutions able to work with this set of limited-data problems. In this study, we employ Abstract Meaning Representation (AMR) graphs as a means to model low-resource Health NLP tasks sourced from various online health resources and communities. AMRs are well suited to model online health texts as they can represent multi-sentence inputs, abstract away from complex terminology, and model long-distance relationships between co-referring tokens. AMRs thus improve the ability of pre-trained language models to reason about high-complexity texts. Our experiments show that we can improve performance on 6 low-resource health NLP tasks by augmenting text embeddings with semantic graph embeddings. Our approach is task agnostic and easy to merge into any standard text classification pipeline. We experimentally validate that AMRs are useful in the modeling of complex texts by analyzing performance through the lens of two textual complexity measures: the Flesch Kincaid Reading Level and Syntactic Complexity. Our error analysis shows that AMR-infused language models perform better on complex texts and generally show less predictive variance in the presence of changing complexity.

Authors: Joseph Gatto, Sarah M. Preum

Last Update: 2023-09-18 00:00:00

Language: English

Source URL: https://arxiv.org/abs/2309.09877

Source PDF: https://arxiv.org/pdf/2309.09877

Licence: https://creativecommons.org/licenses/by/4.0/

Changes: This summary was created with assistance from AI and may have inaccuracies. For accurate information, please refer to the original source documents linked here.

Thank you to arxiv for use of its open access interoperability.

More from authors

Similar Articles