Evaluating Dynamic Topic Models (2024.acl-long)

Copied to clipboard

Challenge: Existing evaluation measures to evaluate the progression of topics in dynamic topic models (DTMs) are difficult due to their unsupervised nature, but are crucial for detecting trends in time-indexed documents.
Approach: They propose to combine topic quality and temporal consistency to evaluate the progression of topics over time in dynamic topic models.
Outcome: The proposed measure correlates well with human judgment and can be used to identify changing topics and evaluate different models and LLMs.

Similar Papers

Beyond Coherence: Improving Temporal Consistency and Interpretability in Dynamic Topic Models (2026.findings-eacl)

Copied to clipboard

Challenge: Existing topic models capture bag-of-words statistics but lack semantic priors . interpretability remains shallow, relying on noisy top-word lists that obscure thematic clarity.
Approach: They propose a variational framework to capture more faithful temporal trajectories . they propose to use entropy-regularized optimal transport to align entire topic constellations .
Outcome: The proposed framework captures more faithful temporal trajectories and improves interpretability.
Dynamic and Static Topic Model for Analyzing Time-Series Document Collections (P18-2)

Copied to clipboard

Challenge: a collection of documents often has dynamic structures, i.e., topics evolve along time depending on multiple topics in the past.
Approach: They propose a dynamic and static topic model that considers dynamic and dynamic structures of topic evolution and static structures of the topic hierarchy at each time.
Outcome: The proposed model outperforms conventional models on scientific papers . it shows that extracted topic structures are useful for analyzing research activities .
Are Neural Topic Models Broken? (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluation paradigms are often divorced from real-world use . recent results have challenged the validity of the prevailing model evaluation paradigm .
Approach: They show that neural topic models fare worse in both respects compared to an established classical method.
Outcome: The proposed method outperforms the members of the ensemble in both respects.
Revisiting Automated Topic Model Evaluation with Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Topic models are an unsupervised dimensionality reduction technique that help organize large text collections.
Approach: They propose to use large language models to evaluate document output and determine optimal number of topics.
Outcome: The proposed model performs better on coherence ratings of word sets than on intrustion detection.
DynaMiTE: Discovering Explosive Topic Evolutions with User Guidance (2023.findings-acl)

Copied to clipboard

Challenge: Existing Dynamic topic models are either fully supervised, requiring expensive human annotations, or fully unsupervised, producing topic evolutions that often do not cater to a user’s needs.
Approach: They propose to use a framework that ensembles semantic similarity, category indicative, and time indicative scores to produce informative topic evolutions.
Outcome: The proposed framework can be used to discover topic evolutions from temporal corpora that align with user-provided category names and uniquely capture topics at each time step.
Topic Model or Topic Twaddle? Re-evaluating Semantic Interpretability Measures (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods for topic model evaluation use automated measures modeled on human evaluation tests that are dissimilar to applied usage.
Approach: They propose to use a novel experimental framework to evaluate topic models and assess their coherence for specialized collections in an applied setting.
Outcome: The proposed framework is reflective of human evaluations using open labeling, typical of applied research.
Improving the TENOR of Labeling: Re-evaluating Topic Models for Content Analysis (2024.eacl-long)

Copied to clipboard

Challenge: Existing evaluation metrics such as coherence and coherency are inadequate for neural topic models.
Approach: They conduct the first evaluation of neural, supervised and classical topic models in an interactive task-based setting.
Outcome: The proposed model performs better on cluster evaluation metrics and human evaluations than classical models on real-world tasks.
TRANSIENTTABLES: Evaluating LLMs’ Reasoning on Temporally Evolving Semi-structured Tables (2025.naacl-long)

Copied to clipboard

Challenge: a recent study shows that large language models are limited in their ability to reason over time due to static datasets.
Approach: They present a dataset that includes 3,971 questions derived from over 14,000 tables . they introduce a template-based question-generation pipeline that harnesses LLMs to refine questions .
Outcome: The proposed model improves on the TRANSIENTTABLES dataset . it demonstrates that the model can reason over time, even when it is not static .
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.
Contextualized Topic Coherence Metrics (2024.findings-eacl)

Copied to clipboard

Challenge: Existing topic models that estimate the interpretability of topics are difficult to compare due to their nature as unsupervised models.
Approach: They propose to use contextualized topic coherence metrics to simulate human-centered coherency evaluation while maintaining the efficiency of other automated methods.
Outcome: The proposed metrics better reflect human judgment on topics extracted from short text collections by avoiding highly scored topics that are meaningless to humans.

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