y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#topic-modeling News & Analysis

5 articles tagged with #topic-modeling. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

5 articles
AINeutralarXiv โ€“ CS AI ยท Apr 156/10
๐Ÿง 

LLM as Attention-Informed NTM and Topic Modeling as long-input Generation: Interpretability and long-Context Capability

Researchers propose a novel framework treating Large Language Models as attention-informed Neural Topic Models, enabling interpretable topic extraction from documents. The approach combines white-box interpretability analysis with black-box long-context LLM capabilities, demonstrating competitive performance on topic modeling tasks while maintaining semantic clarity.

AINeutralarXiv โ€“ CS AI ยท Mar 54/10
๐Ÿง 

TopicENA: Enabling Epistemic Network Analysis at Scale through Automated Topic-Based Coding

TopicENA is a new framework that combines BERTopic with Epistemic Network Analysis to automatically analyze concept relationships in large text datasets without manual coding. The research demonstrates that automated topic modeling can replace expert manual coding while maintaining analytical quality, making network analysis scalable for large corpora.

AINeutralarXiv โ€“ CS AI ยท Mar 54/10
๐Ÿง 

CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents

Researchers have created CzechTopic, a new benchmark dataset for evaluating AI models' ability to identify specific topics within historical Czech documents. The study compared various large language models and BERT-based models, finding significant performance variations with the strongest models approaching human-level accuracy in topic detection.

AINeutralarXiv โ€“ CS AI ยท Mar 34/103
๐Ÿง 

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

Researchers introduce Topic Word Mixing (TWM), a new human evaluation method for assessing topic models in specialized domains. The study reveals misalignment between automated metrics and human judgment, particularly in domain-specific corpora like philosophy of science publications.

AIBullishHugging Face Blog ยท May 314/109
๐Ÿง 

Introducing BERTopic Integration with the Hugging Face Hub

BERTopic, a popular topic modeling library, has integrated with the Hugging Face Hub to enable easier sharing and discovery of topic models. This integration allows researchers and practitioners to upload, download, and collaborate on BERTopic models through Hugging Face's platform.