Toward Keyword Generation through Large Language Models

• DOI: 10.1145/3581754.3584126
• Publication Date: 2023-03-26T22:12:25Z
• Authors: Wanhae Lee; Minki Chun; Hyeonhak Jeong; Hyunggu Jung
• Keywords: Natural Language Generation

It is essential to understand research trends for researchers, decision-makers, and investors. One way analyze collect author-defined keywords in scientific papers. Unfortunately, while are beneficial researchers aiming figure out the of their fields, 45% papers Microsoft Academic Graph did not contain keywords. Additionally, six top seven AI conferences neither nor disclose This paper proposes a method generating using Galactica, pre-trained large language model published by Meta. We evaluate this method's performance comparing provided authors CoRL'22 report characteristics generated Our study shows F1 score our proposed was ten times better than that previous studies, 42.7% relevant