adf08b3e0f1bcfb9b3b2 · Improving the TENOR of Labeling: Re-evaluating Topic Models for Content Analysis
Improving the TENOR of Labeling: Re-evaluating Topic Models for Content Analysis
Topic models are a popular tool for understanding text collections, but their evaluation has been a point of contention. Automated evaluation metrics such as coherence are often used, however, their validity has been questioned for neural topic models
{
"title_en": "Improving the TENOR of Labeling: Re-evaluating Topic Models for Content Analysis",
"designation": "",
"series": "",
"status": "",
"date": "2024-03-23",
"date_original": "March 23, 2024",
"url": "https://www.nist.gov/publications/improving-tenor-labeling-re-evaluating-topic-models-content-analysis",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Zongxia Li, Andrew Mao, Jordan Boyd-Graber, Daniel Stephens, Emily Walpole , Alden A. Dima , Juan Fung",
"abstract_excerpt_en": "Topic models are a popular tool for understanding text collections, but their evaluation has been a point of contention. Automated evaluation metrics such as coherence are often used, however, their validity has been questioned for neural topic models",
"id": "adf08b3e0f1bcfb9b3b2",
"sources": [
"NIST Publications"
],
"source_records": [
{
"title_en": "Improving the TENOR of Labeling: Re-evaluating Topic Models for Content Analysis",
"designation": "",
"series": "",
"status": "",
"date": "2024-03-23",
"date_original": "March 23, 2024",
"url": "https://www.nist.gov/publications/improving-tenor-labeling-re-evaluating-topic-models-content-analysis",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Zongxia Li, Andrew Mao, Jordan Boyd-Graber, Daniel Stephens, Emily Walpole , Alden A. Dima , Juan Fung",
"abstract_excerpt_en": "Topic models are a popular tool for understanding text collections, but their evaluation has been a point of contention. Automated evaluation metrics such as coherence are often used, however, their validity has been questioned for neural topic models"
}
],
"translation_state": "none"
}