Foundation models for topic modeling: a case study  

作　　者：Han ZENG Jia-Ming SUN Chun-Shu LI Zhuying LI Tong WEI 

机构地区：[1]School of Computer Science and Engineering,Southeast University,Nanjing 210096,China [2]Key Laboratory of Computer Network and Information Integration,Southeast University,Nanjing 210096,China

出　　处：《Frontiers of Computer Science》2025年第2期129-131,共3页计算机科学前沿(英文版)

摘　　要：1 Introduction In Natural Language Processing(NLP),topic modeling is a class of methods used to analyze and explore textual corpora,i.e.,to discover the underlying topic structures from text and assign text pieces to different topics.In NLP,a topic means a set of relevant words appearing together in a particular pattern,representing some specific information.It is beneficial for tracking social media trends,constructing knowledge graphs,and analyzing writing styles.Topic modeling has always been an area of extensive research in NLP.Traditional methods like Latent Semantic Analysis(LSA)and Latent Dirichlet Allocation(LDA),based on the“bag of words”(BoW)model,often fail to grasp the semantic nuances of the text,making them less effective in contexts involving polysemy or data noise,especially when the amount of data is small.

关 键 词：WORDS SEMANTIC TEXTUAL 

分 类 号：H31[语言文字—英语]