Disentangling transformer language models as superposed topic models

Disentangling transformer language models as superposed topic models

Topic Modelling is an established research area where the quality of a given topic is measured using coherence metrics. Often, we infer topics from Neural Topic Models (NTM) by interpreting their decoder weights, consisting of top-activated words projected from individual neurons. Transformer-based...

Full description

Saved in:
Bibliographic Details
Main Authors: LIM, Jia Peng, LAUW, Hady Wirawan
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Databases and Information Systems
Programming Languages and Compilers
Online Access:https://ink.library.smu.edu.sg/sis_research/8470
https://ink.library.smu.edu.sg/context/sis_research/article/9473/viewcontent/2023.emnlp_main.534__1_.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English

Internet

https://ink.library.smu.edu.sg/sis_research/8470
https://ink.library.smu.edu.sg/context/sis_research/article/9473/viewcontent/2023.emnlp_main.534__1_.pdf

Similar Items