Topic Modeling in Embedding Spaces (2020.tacl-1)

Copied to clipboard

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

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 .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations