# šŸ’ƒšŸ¼ Topic Modeling SIG **URL:** https://forum.webuddhist.com/c/sig/topic-modeling/18.md [Latest](https://forum.webuddhist.com/latest.md) Ā· [Categories](https://forum.webuddhist.com/categories.md) Ā· [Tags](https://forum.webuddhist.com/tags.md) --- ## [About the šŸ’ƒšŸ¼ Topic Modeling SIG category](https://forum.webuddhist.com/t/about-the-topic-modeling-sig-category/119)
**Author:** [@uchiha\_tashi](https://forum.webuddhist.com/u/uchiha_tashi)\ **Replies:** 0
--- ## [Domain Tagging With Supervised Classification for Retrieval Augmented Translation](https://forum.webuddhist.com/t/domain-tagging-with-supervised-classification-for-retrieval-augmented-translation/188)
**Author:** [@billingsmoore](https://forum.webuddhist.com/u/billingsmoore)\ **Replies:** 0\ **Last updated:** [January 17, 2025, 2:09am UTC](https://forum.webuddhist.com/t/domain-tagging-with-supervised-classification-for-retrieval-augmented-translation/188 "2025-01-17T02:09:12Z")
Domain Tagging With Supervised Clustering for Retrieval Augmented Translation Introduction In a previous post, Domain Tagging With Unsupervised Clustering for Retrieval Augmented Translation, I created domain tags for thā€¦ --- ## [Using Topic Modeling to Cluster User Translation (BERTopic)](https://forum.webuddhist.com/t/using-topic-modeling-to-cluster-user-translation-bertopic/111)
**Author:** [@uchiha\_tashi](https://forum.webuddhist.com/u/uchiha_tashi)\ **Replies:** 0\ **Last updated:** [November 28, 2024, 6:57am UTC](https://forum.webuddhist.com/t/using-topic-modeling-to-cluster-user-translation-bertopic/111 "2024-11-28T06:57:20Z")
Using Topic Modeling to Cluster User Translation (BERTopic) Introduction We live in a world overflowing with unstructured textā€”customer emails, online reviews, tweets, academic papers, and so much more. Believe it or notā€¦ --- ## [A Pipeline for Tibetan Language Text Clustering](https://forum.webuddhist.com/t/a-pipeline-for-tibetan-language-text-clustering/197)
**Author:** [@billingsmoore](https://forum.webuddhist.com/u/billingsmoore)\ **Replies:** 0\ **Last updated:** [February 18, 2025, 2:59am UTC](https://forum.webuddhist.com/t/a-pipeline-for-tibetan-language-text-clustering/197 "2025-02-18T02:59:15Z")
A Pipeline for Tibetan Language Text Clustering Introduction Text clustering is a natural language processing task in which pieces of text (sometimes referred to as ā€œdocumentsā€) are grouped, or ā€œclusteredā€, based on simiā€¦ --- ## [Domain Tagging With Unsupervised Clustering for Retrieval Augmented Translation](https://forum.webuddhist.com/t/domain-tagging-with-unsupervised-clustering-for-retrieval-augmented-translation/173)
**Author:** [@billingsmoore](https://forum.webuddhist.com/u/billingsmoore)\ **Replies:** 0\ **Last updated:** [December 25, 2024, 4:21am UTC](https://forum.webuddhist.com/t/domain-tagging-with-unsupervised-clustering-for-retrieval-augmented-translation/173 "2024-12-25T04:21:15Z")
Domain Tagging With Unsupervised Clustering for Retrieval Augmented Translation A previous version of this post mistakenly omitted non-Buddhist material from the analysis. This has now been corrected. Introduction For rā€¦ --- ## [Toward a Cleaner Translation Dataset](https://forum.webuddhist.com/t/toward-a-cleaner-translation-dataset/72)
**Author:** [@billingsmoore](https://forum.webuddhist.com/u/billingsmoore)\ **Replies:** 0\ **Last updated:** [November 3, 2024, 4:38pm UTC](https://forum.webuddhist.com/t/toward-a-cleaner-translation-dataset/72 "2024-11-03T16:38:01Z")
Toward a Cleaner Translation Dataset Introduction While performing topic modeling on the translation dataset ā€˜openpecha/cleaned\_MT\_v1.0.2ā€™ it was discovered that some elements (ā€˜sentence pairsā€™) of the dataset may presenā€¦ --- ## [Hyperparameter Optimization for Topic Modeling](https://forum.webuddhist.com/t/hyperparameter-optimization-for-topic-modeling/100)
**Author:** [@billingsmoore](https://forum.webuddhist.com/u/billingsmoore)\ **Replies:** 0\ **Last updated:** [November 23, 2024, 11:12pm UTC](https://forum.webuddhist.com/t/hyperparameter-optimization-for-topic-modeling/100 "2024-11-23T23:12:28Z")
Hyperparameter Optimization for Translation Topic Modeling In addition to my previous posts using topic modeling as a tool for data mining in the translation dataset, topic modeling is also used to understand what contenā€¦ --- ## [Topic Modeling Buddhist Material in the Translation Dataset](https://forum.webuddhist.com/t/topic-modeling-buddhist-material-in-the-translation-dataset/91)
**Author:** [@billingsmoore](https://forum.webuddhist.com/u/billingsmoore)\ **Replies:** 0\ **Last updated:** [November 21, 2024, 9:49pm UTC](https://forum.webuddhist.com/t/topic-modeling-buddhist-material-in-the-translation-dataset/91 "2024-11-21T21:49:06Z")
Topic Modeling Buddhist Material in the Translation Dataset Following results from Modeling the Full Translation Dataset, obviously non-Buddhist materials were excluded from the dataset and topic modeling was conducted oā€¦ --- ## [Modeling the Full Translation Dataset](https://forum.webuddhist.com/t/modeling-the-full-translation-dataset/85)
**Author:** [@billingsmoore](https://forum.webuddhist.com/u/billingsmoore)\ **Replies:** 0\ **Last updated:** [November 12, 2024, 10:13pm UTC](https://forum.webuddhist.com/t/modeling-the-full-translation-dataset/85 "2024-11-12T22:13:32Z")
Modeling the Full Translation Dataset Summary Following results from ā€™ A First Look at Topic Modeling for the Translation Datasetā€™, topic modeling was conducted the full translation dataset openpecha/cleaned\_MT\_v1.0.2. Tā€¦ --- ## [A First Look at Topic Modeling for the Translation Dataset](https://forum.webuddhist.com/t/a-first-look-at-topic-modeling-for-the-translation-dataset/70)
**Author:** [@billingsmoore](https://forum.webuddhist.com/u/billingsmoore)\ **Replies:** 0\ **Last updated:** [October 28, 2024, 9:12pm UTC](https://forum.webuddhist.com/t/a-first-look-at-topic-modeling-for-the-translation-dataset/70 "2024-10-28T21:12:57Z")
A First Look at Topic Modeling for the Translation Dataset To better understand the content of the translation dataset, Iā€™ve conducted some basic topic modeling. The dataset used is the English portion of the sentence paā€¦