This package is hidden from search results because it is not hosted in the universe of the upstream ownersonsoleslp. To fix this you can add URL: https://mohsaqr.r-universe.dev/sbert to the package DESCRIPTION file. See also theR-universe documentation.

Package: sbert 0.5.8

Sonsoles López-Pernas

sbert: Topic Modeling with 'Sentence-BERT' Embeddings

Builds semantic topic models from 'Sentence-BERT' embeddings (Reimers and Gurevych, 2019) <doi:10.18653/v1/D19-1410>. Sentence embeddings are computed in several modes with models run on the Open Neural Network Exchange ('ONNX') Runtime, including multilingual and long-context encoders and a fast static model. Topics are labeled with class-based term weighting that can be retuned without refitting. Candidate topic counts and document granularities (whole documents, sentences, clauses, or phrases) can be compared side by side, and fitted models assign topics to new documents, give soft memberships and per-document topic mixtures. The package offers coherence and diversity metrics and visualizations.

Authors:Mohammed Saqr [aut, cph], Sonsoles López-Pernas [aut, cre, cph]

sbert_0.5.8.tar.gz
sbert_0.5.8.zip(r-4.7-any)sbert_0.5.8.zip(r-4.6-any)sbert_0.5.8.zip(r-4.5-any)
sbert_0.5.8.tgz(r-4.6-any)sbert_0.5.8.tgz(r-4.5-any)
sbert_0.5.8.tar.gz(r-4.7-any)sbert_0.5.8.tar.gz(r-4.6-any)
sbert_0.5.8.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
sbert/json (API)

# Install 'sbert' in R:

install.packages('sbert', repos = c('https://mohsaqr.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/sonsoleslp/sbert/issues

Pkgdown/docs site:https://sonsoles.me

Datasets:

covid - COVID-19 Research Abstracts
feedback_translations - AI-generated Mathematics Feedback with English Translations

On CRAN:

bert embeddings nlp onnx sentence-embeddings sentence-transformers topic-modeling

3.54 score 34 exports 6 dependencies

Last updated from:387023d12e. Checks:9 OK. Indexed: no.

Target	Result	Time
linux-devel	OK	140
source / vignettes	OK	248
linux-release	OK	132
macos-release	OK	95
macos-oldrel	OK	107
windows-devel	OK	74
windows-release	OK	96
windows-oldrel	OK	100
wasm-release	OK	115

Exports:abbreviations blend cache_dir cache_size clean_corpus coherence compare_topics content_ratio dedupe encode install_runtime keywords load_custom load_model model_download model_remove model_status models pool reduce_topics representatives segment select_topics stop_words strip_list_markers topic_corpus topic_diversity topic_gamma topic_hierarchy topic_membership topic_palette topic_similarity topic_sizes topics

Dependencies:cli cpp11 digest onnxr R6 tok

Semantic Topics in AI-Powered Mathematics Feedback

Rendered frommath_vignette.Rmdusingknitr::rmarkdown

Last update: 2026-10-09
Started: 2026-09-28

Help page	Topics
Obtain the Built-in Abbreviation Gazetteer	abbreviations
Coerce a Topic-Count Comparison to a Data Frame	as.data.frame.sbert_topic_sweep
Blend Segment Embeddings with Their Document Context	blend
Locate the sbert Model Cache	cache_dir
Measure the sbert Cache	cache_size
Clean a Text Corpus Before Encoding	clean_corpus
Score Topic Coherence	coherence
Compare Topic Counts Before Committing to One	compare_topics
Alphabetic Content Ratio of Text	content_ratio
COVID-19 Research Abstracts	covid
Deduplicate a Text Corpus with Frequencies	dedupe
Encode Text with Sentence-BERT	encode
AI-generated Mathematics Feedback with English Translations	feedback_translations
Extract One Fitted Model from a Topic-Count Comparison	fitted.sbert_topic_sweep
Install ONNX Runtime	install_runtime
Extract Keywords from Documents by Embedding Similarity	keywords
Load an Arbitrary Hugging Face Embedding Model	load_custom
Load a Pinned Sentence-BERT Model	load_model
Download a Pinned Sentence-BERT Model	model_download
Remove an Installed Model from the Cache	model_remove
Inspect an Installed Model	model_status
List the Available Pinned Sentence-BERT Models	models
Plot a Topic Hierarchy Dendrogram	plot.sbert_topic_hierarchy
Plot a Semantic Topic Model	plot.sbert_topic_model
Plot a Topic-Count Comparison	plot.sbert_topic_sweep
Pool Token Embeddings into Sentence Embeddings	pool
Assign New Documents to Fitted Topics	predict.sbert_topic_model
Print a Loaded Model	print.sbert_model
Print a Prepared Topic Corpus	print.sbert_topic_corpus
Print a Topic Hierarchy	print.sbert_topic_hierarchy
Print a Semantic Topic Model	print.sbert_topic_model
Print a Topic-Count Comparison	print.sbert_topic_sweep
Reduce a Fitted Topic Model to Fewer Topics	reduce_topics
Representative Text Units for Every Topic	representatives
Segment Text into Sentences, Clauses, or Phrases	segment
Obtain and Adjust the Topic Stop-Word List	stop_words
Strip Enumeration and List Markers from Text	strip_list_markers
Summarize a Semantic Topic Model	summary.sbert_topic_model
Topic Terms, Retuned Without Refitting	terms.sbert_topic_model
Prepare a Corpus Once to Fit Many Topic Models	topic_corpus
Measure Topic Diversity	topic_diversity
Document-Topic Distributions from Segment Assignments	topic_gamma
Build the Topic Hierarchy of a Fitted Model	topic_hierarchy
Soft Topic Membership Probabilities	topic_membership
Qualitative Colour Palette for Topics	topic_palette
Compute Cosine Similarity	topic_similarity
Topic Sizes on the Distinct and Weighted Scales	topic_sizes
Discover Semantic Topics in Documents	topics

Package: sbert 0.5.8

sbert: Topic Modeling with 'Sentence-BERT' Embeddings

Citation

Development and contributors

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)