TopicTag: Automatic Annotation of NMF Topic Models Using Chain of Thought and Prompt Tuning with LLMs

Autor:	Wanna, Selma, Barron, Ryan, Solovyev, Nick, Eren, Maksim E., Bhattarai, Manish, Rasmussen, Kim, Alexandrov, Boian S.
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	Topic modeling is a technique for organizing and extracting themes from large collections of unstructured text. Non-negative matrix factorization (NMF) is a common unsupervised approach that decomposes a term frequency-inverse document frequency (TF-IDF) matrix to uncover latent topics and segment the dataset accordingly. While useful for highlighting patterns and clustering documents, NMF does not provide explicit topic labels, necessitating subject matter experts (SMEs) to assign labels manually. We present a methodology for automating topic labeling in documents clustered via NMF with automatic model determination (NMFk). By leveraging the output of NMFk and employing prompt engineering, we utilize large language models (LLMs) to generate accurate topic labels. Our case study on over 34,000 scientific abstracts on Knowledge Graphs demonstrates the effectiveness of our method in enhancing knowledge management and document organization. Comment: Accepted to ACM Symposium on Document Engineering 2024 (DocEng 24), 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2407.19616 Zobrazit plný text záznamu View this record from Arxiv