NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pham, Duy-Tung, Vu, Thien Trang Nguyen, Nguyen, Tung, Van, Linh Ngo, Nguyen, Duc Anh, Nguyen, Thien Huu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910624384024576
author Pham, Duy-Tung
Vu, Thien Trang Nguyen
Nguyen, Tung
Van, Linh Ngo
Nguyen, Duc Anh
Nguyen, Thien Huu
author_facet Pham, Duy-Tung
Vu, Thien Trang Nguyen
Nguyen, Tung
Van, Linh Ngo
Nguyen, Duc Anh
Nguyen, Thien Huu
contents Recent advances in neural topic models have concentrated on two primary directions: the integration of the inference network (encoder) with a pre-trained language model (PLM) and the modeling of the relationship between words and topics in the generative model (decoder). However, the use of large PLMs significantly increases inference costs, making them less practical for situations requiring low inference times. Furthermore, it is crucial to simultaneously model the relationships between topics and words as well as the interrelationships among topics themselves. In this work, we propose a novel framework called NeuroMax (Neural Topic Model with Maximizing Mutual Information with Pretrained Language Model and Group Topic Regularization) to address these challenges. NeuroMax maximizes the mutual information between the topic representation obtained from the encoder in neural topic models and the representation derived from the PLM. Additionally, NeuroMax employs optimal transport to learn the relationships between topics by analyzing how information is transported among them. Experimental results indicate that NeuroMax reduces inference time, generates more coherent topics and topic groups, and produces more representative document embeddings, thereby enhancing performance on downstream tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19749
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization
Pham, Duy-Tung
Vu, Thien Trang Nguyen
Nguyen, Tung
Van, Linh Ngo
Nguyen, Duc Anh
Nguyen, Thien Huu
Computation and Language
Recent advances in neural topic models have concentrated on two primary directions: the integration of the inference network (encoder) with a pre-trained language model (PLM) and the modeling of the relationship between words and topics in the generative model (decoder). However, the use of large PLMs significantly increases inference costs, making them less practical for situations requiring low inference times. Furthermore, it is crucial to simultaneously model the relationships between topics and words as well as the interrelationships among topics themselves. In this work, we propose a novel framework called NeuroMax (Neural Topic Model with Maximizing Mutual Information with Pretrained Language Model and Group Topic Regularization) to address these challenges. NeuroMax maximizes the mutual information between the topic representation obtained from the encoder in neural topic models and the representation derived from the PLM. Additionally, NeuroMax employs optimal transport to learn the relationships between topics by analyzing how information is transported among them. Experimental results indicate that NeuroMax reduces inference time, generates more coherent topics and topic groups, and produces more representative document embeddings, thereby enhancing performance on downstream tasks.
title NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization
topic Computation and Language
url https://arxiv.org/abs/2409.19749