paper-with-me

홈 › Papers

Diversity-Aware Coherence Loss for Improving Neural Topic Models

2023-05-25 · Raymond Li, Felipe González-Pizarro, Linzi Xing, Gabriel Murray, Giuseppe Carenini

The standard approach for neural topic modeling uses a variational autoencoder (VAE) framework that jointly minimizes the KL divergence between the estimated posterior and prior, in addition to the reconstruction loss. Since neural topic models are trained by recreating individual input documents, they do not explicitly capture the coherence between topic words on the corpus level. In this work, we propose a novel diversity-aware coherence loss that encourages the model to learn corpus-level coherence scores while maintaining a high diversity between topics. Experimental results on multiple datasets show that our method significantly improves the performance of neural topic models without requiring any pretraining or additional parameters.

📄 PDF Abstract BibTeX arXiv:2305.16199

Code (1)

raymondzmc/topic-model-diversity-aware-coherence-loss 공식 구현 pytorch

Tasks

DiversityTopic Models

Similar Papers 제목 키워드 기반

Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversity

2018-09-18 · Xinnuo Xu, Ondřej Dušek, Ioannis Konstas, Verena Rieser

We present three enhancements to existing encoder-decoder models for open-domain conversational agents, aimed at effectively modeling coherence and promoting output diversity: (1) We introduce a measure of coherence as t…

DecoderDiversity

Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity

2018-10-01 · EMNLP 2018 10 · Xinnuo Xu, Ond{\v{r}}ej Du{\v{s}}ek, Ioannis Konstas, Verena Rieser

We present three enhancements to existing encoder-decoder models for open-domain conversational agents, aimed at effectively modeling coherence and promoting output diversity: (1) We introduce a measure of coherence as t…

DecoderDialogue GenerationDiversity

Coherence-Aware Neural Topic Modeling

2018-09-07 · EMNLP 2018 10 · Ran Ding, Ramesh Nallapati, Bing Xiang

Topic models are evaluated based on their ability to describe documents well (i.e. low perplexity) and to produce topics that carry coherent semantic meaning. In topic modeling so far, perplexity is a direct optimization…

Topic ModelsVariational Inference

Human-Centric Topic Modeling with Goal-Prompted Contrastive Learning and Optimal Transport

2026-04-14 · Rui Wang, Yi Zheng, Dongxin Wang, Haiping Huang 외 arxiv

Existing topic modeling methods, from LDA to recent neural and LLM-based approaches, which focus mainly on statistical coherence, often produce redundant or off-target topics that miss the user's underlying intent. We in…

Contrastive Learning

When Numbers Tell Half the Story: Human-Metric Alignment in Topic Model Evaluation

2026-03-02 · Thibault Prouteau, Francis Lareau, Nicolas Dugué, Jean-Charles Lamirel 외 arxiv

Topic models uncover latent thematic structures in text corpora, yet evaluating their quality remains challenging, particularly in specialized domains. Existing methods often rely on automated metrics like topic coherenc…

Topic Models