챗GPT 관련 요약문에서 기술 신조어 추출과 단어 임베딩
ChatGPT-related Technology Neologism Extraction and Word Embedding in Paper Abstracts
- 발행
- 2024 등록이 논문은 발행 시점을 확인하지 못해 원문 등록일을 적었습니다. KCI가 2005~2008년에 옛 논문을 몰아서 올린 탓에, 그 시기 등록분은 발행보다 평균 3~5년 늦습니다. 실제 발행연도는 더 이를 수 있습니다.
- 소속·발행
- 충남대학교
- 출처
- 국내 KCI
- DOI
- 10.18627/jslg.40.2.202408.109
- 원문
- 원문 보기 ↗
개념
키워드
챗GPT, LLM, 전산언어학, 신조어 추출, 단어임베딩, ChatGPT, Large Language Model, Computational Linguistics, Neologism Extraction, Word Embedding
초록
This study aims to analyze the recent innovative changes in LLMs related to ChatGPT through neologism extraction and word embedding analysis. To this end, this paper collects 26,010 abstracts of international academic papers related to ChatGPT from November 2022 to April 2024. It extracts and analyzes the neologisms appearing in these abstracts by focusing on acronyms. Acronyms are frequently used in scientific texts such as AI or ChatGPT. The paper also analyzes the characteristics of word embedding, which quantifies the semantic similarity of words in the abstracts and seeks to understand and utilize how new concepts and terms are introduced and spread in the field of natural language processing. This research is one proper methodology for knowledge discovery