Towards reinterpreting neural topic models via composite activations

• Main Authors: LIM, Jia Peng, LAUW, Hady Wirawan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: topic modeling; composite topics; empirical study; machine learning; neural networks; Artificial Intelligence and Robotics
• Online Access: https://ink.library.smu.edu.sg/sis_research/7610; https://ink.library.smu.edu.sg/context/sis_research/article/8613/viewcontent/emnlp22.pdf
• Institution: Singapore Management University

Most Neural Topic Models (NTM) use a variational auto-encoder framework producing K topics limited to the size of the encoder’s output. These topics are interpreted through the selection of the top activated words via the weights or reconstructed vector of the decoder that are directly connected to each neuron. In this paper, we present a model-free two-stage process to reinterpret NTM and derive further insights on the state of the trained model. Firstly, building on the original information from a trained NTM, we generate a pool of potential candidate “composite topics” by exploiting possible co-occurrences within the original set of topics, which decouples the strict interpretation of topics from the original NTM. This is followed by a combinatorial formulation to select a final set of composite topics, which we evaluate for coherence and diversity on a large external corpus. Lastly, we employ a user study to derive further insights on the reinterpretation process.