띄어쓰기(특히 괄호 뒤)

• 예: Country (e.g., Korea)

약어 사용

• 처음 정의할 때만 Full name 기재, 이후에는 약어(Acronym) 사용

• 2번 이상 사용되는 경우 약어 정의

• 예: Convolutional neural network (CNN)

줄임말 표현

• i.e. / e.g. / cf.

• 예: Neural networks (e.g., convolutional networks)

논문 논리 흐름 구성

• Big problem - Specific challenge - Your approach

Abstract 작성 요령

• Importance

• Research gap

• Objective

• Method

• Key findings & Implications

Introduction 작성 요령(4가지 핵심 요소 포함)

• Scope of work

• Importance

• Background knowledge

• Arrangement of paper

Conclusion 작성 요령(기본 4문단 구성)

• Summary of work

• 제안한 방법 설명(Step by step으로)

• Case study 및 실험 결과 정리

• Future works

• 예:

  • Empirical risk minimization (ERM) provides a principled guideline for many machine learning and data mining algorithms. Under the ERM principle, one minimizes an upper bound of the true risk, which is approximated by the summation of empirical risk and the complexity of the candidate classifier class. To guarantee a satisfactory learning performance, ERM requires that the training data are i.i.d. sampled from the unknown source distribution. However, this may not be the case in active learning, where one selects the most informative samples to label, and these data may not follow the source distribution. In this article, we generalize the ERM principle to the active learning setting. We derive a novel form of upper bound for the true risk in the active learning setting; by minimizing this upper bound, we develop a practical batch-mode active learning method. The proposed formulation involves a nonconvex integer programming optimization problem. We solve it efficiently by an alternating optimization method. Our method is shown to query the most informative samples while preserving the source distribution as much as possible, thus identifying the most uncertain and representative queries. We further extend our method to multiclass active learning by introducing novel pseudolabels in the multiclass case and developing an efficient algorithm. Experiments on benchmark datasets and real-world applications demonstrate the superior performance of our proposed method compared to state-of-the-art methods. (Excerpt from: https://dl.acm.org/doi/10.1145/2700408)

잡다한 팁들

• Such as / Which / Since 앞에는 꼭 쉼표(,) 사용

  • 예: countries, such as Korea

• Not only "~" but also "~": "~"에 Noun이 오면 가운데 쉼표 사용 X / Clause가 오면 쉼표 사용 O

• A lot of 는 사용 지양 / A large number of 등의 표현으로 대체

• Because는 이유/원인이 중요 vs. Since는 결과가 중요

• 여러 논문을 한번에 괄호안에 넣을때에는 시간 순 / 저자 순으로

• 논문에서는 축약형 표현 사용 지양

  • 예: Do not contain (vs. Don't contain)

• 숫자 천의 자리마다 쉼표 표기

  • 예: USD 400,000

• 그래프 왼쪽 및 오른쪽 끝과 그림 모서리 맞추기(빈 공간 없도록)

• Novelty 강조

  • 예: The primary novelty comes from the scheduling of the weights for mixing the pseudo-labels