| Challenge: | Existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. |
| Approach: | They propose an embedded topic model that integrates word embeddings with a categorical distribution that is the natural parameter between the word’s embeddment and an embeddement of its assigned topic. |
| Outcome: | The embedded topic model outperforms existing topic models in terms of topic quality and predictive performance. |
Similar Papers
Topic Modeling: Contextual Token Embeddings Are All You Need (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Current neural approaches to topic modeling have not been able to solve all of the problems. |
| Approach: | They propose a topic modeling approach that uses document contextual token embeddings to find topics and find topic spans within documents. |
| Outcome: | The proposed model outperforms the current state-of-the-art models on a comprehensive set of topic model evaluation metrics. |
Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too! (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing topic models rely on probabilistic models to uncover themes within document collections, but are they the only option? |
| Approach: | They propose a way to cluster pre-trained word embeddings while incorporating document information for weighted clustering and reranking top words. |
| Outcome: | The proposed approach performs as well as classical topic models, but with lower runtime and computational complexity. |
Multi-source Neural Topic Modeling in Multi-view Embedding Spaces (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work has used pre-trained word embeddings to address data sparsity in short-text or small document collections. |
| Approach: | They propose a neural topic modeling framework using multi-view embedding spaces to improve topic quality and deal with polysemy. |
| Outcome: | The proposed framework improves topic quality and deal with polysemy. |
A Neural Generative Model for Joint Learning Topics and Topic-Specific Word Embeddings (2020.tacl-1)
Copied to clipboard
| Challenge: | Experimental results show that the proposed model outperforms word-level embedding methods in word similarity evaluation and word sense disambiguation. |
| Approach: | They propose a generative model that explores local and global context for joint learning topics and topic-specific word embeddings. |
| Outcome: | The proposed model outperforms word-level embedding methods in word similarity evaluation and word sense disambiguation. |
Neural Attention-Aware Hierarchical Topic Model (2021.emnlp-main)
Copied to clipboard
| Challenge: | Neural topic models (NTMs) use deep neural networks to learn topic information. |
| Approach: | They propose a variational autoencoder model that reconstructs sentence and document word counts using bag-of-words embeddings and pre-trained semantic embedders. |
| Outcome: | The proposed model lowers reconstruction errors at sentence and document levels and finds more coherent topics from real-world datasets. |
Dynamic Topic Modeling by Clustering Embeddings from Pretrained Language Models: A Research Proposal (2022.aacl-srw)
Copied to clipboard
| Challenge: | Neural Topic Models (NTMs) are topic models that are created with the help of a pretrained language model. |
| Approach: | They propose to do Neural Topic Modeling by Clustering document Embeddings (NTM-CE) with a pretrained language model to create dynamic topic models. |
| Outcome: | The proposed model can be evaluated theoretically and practically using quantitative measurements of coherence and human evaluation to evaluate the model. |
CAST: Corpus-Aware Self-similarity Enhanced Topic modelling (2025.naacl-long)
Copied to clipboard
Yanan Ma, Chenghao Xiao, Chenhan Yuan, Sabine N Van Der Veer, Lamiece Hassan, Chenghua Lin, Goran Nenadic
| Challenge: | Existing topic modelling methods encode contextual information of documents while ignoring contextual details of candidate centroid words. Existing methods are limited by the contextualization gap. |
| Approach: | They propose a topic modelling method that builds upon candidate centroid word embeddings contextualized on the dataset and a self-similarity-based method to filter out less meaningful tokens. |
| Outcome: | The proposed method significantly enhances the coherence and diversity of generated topics, and handles noisy data, outperforming strong baselines. |
Modeling Text using the Continuous Space Topic Model with Pre-Trained Word Embeddings (2021.acl-srw)
Copied to clipboard
| Challenge: | Existing topic models that extract latent topics from text are based on latent topic and do not use intermediate variables such as latent subjects. |
| Approach: | They propose a model that extends the continuous space topic model (CSTM) they pre-train word embeddings which capture the semantics of words and plug them into the CSTM . |
| Outcome: | The proposed model performs better than the baseline model in terms of perplexity and convergence speed. |
Topic Modeling by Clustering Language Model Embeddings: Human Validation on an Industry Dataset (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Topic models are powerful tools to get overview of large collections of text data. |
| Approach: | They propose to use a tool called STELLAR for interactive topic browsing to evaluate topics from a real-world dataset. |
| Outcome: | The proposed model performs better than LDA models in the real-world and is scalable. |
Rethinking Topic Modelling: From Document-Space to Term-Space (2020.findings-emnlp)
Copied to clipboard
| Challenge: | a paper examines the use of document-based topic models for defining term interactions . term-based models outperform document-derived models by a large margin, the authors argue . |
| Approach: | They propose to reformulate topic distributions as latent factors in term similarity space . they use word embeddings built with wide context windows to test their approach . |
| Outcome: | The proposed model outperforms standard document-based models by a large margin . the proposed model is less sensitive to document formatting and more precise . |