{ "_id": "6ac958a9de46216d5edda5a5", "Package": "sbert", "Type": "Package", "Title": "Topic Modeling with 'Sentence-BERT' Embeddings", "Version": "0.5.8", "Authors@R": "c(\nperson(\ngiven = \"Mohammed\",\nfamily = \"Saqr\",\nrole = c(\"aut\", \"cph\"),\nemail = \"mohammed.saqr@uef.fi\",\ncomment = c(ORCID = \"0000-0001-5881-3109\")\n),\nperson(\ngiven = \"Sonsoles\",\nfamily = \"L\\u00f3pez-Pernas\",\nrole = c(\"aut\", \"cre\", \"cph\"),\nemail = \"sonsoles.lopez@uef.fi\",\ncomment = c(ORCID = \"0000-0002-9621-1392\")\n)\n)", "Description": "Builds semantic topic models from 'Sentence-BERT'\nembeddings (Reimers and Gurevych, 2019)\n. Sentence embeddings are computed in\nseveral modes with models run on the Open Neural Network\nExchange ('ONNX') Runtime, including multilingual and\nlong-context encoders and a fast static model. Topics are\nlabeled with class-based term weighting that can be retuned\nwithout refitting. Candidate topic counts and document\ngranularities (whole documents, sentences, clauses, or phrases)\ncan be compared side by side, and fitted models assign topics\nto new documents, give soft memberships and per-document topic\nmixtures. The package offers coherence and diversity metrics\nand visualizations.", "License": "MIT + file LICENSE", "URL": "https://sonsoles.me/sbert/, https://github.com/sonsoleslp/sbert", "BugReports": "https://github.com/sonsoleslp/sbert/issues", "Encoding": "UTF-8", "Language": "en-US", "LazyData": "true", "SystemRequirements": "ONNX Runtime (>= 1.25.1)", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "RoxygenNote": "8.0.0", "Config/pak/sysreqs": "libclang-dev", "Repository": "https://mohsaqr.r-universe.dev", "Date/Publication": "2026-10-09 17:03:24 UTC", "RemoteUrl": "https://github.com/sonsoleslp/sbert", "RemoteRef": "HEAD", "RemoteSha": "387023d12ebc6cc73b8a32332fcc60c56ad79af7", "NeedsCompilation": "no", "Packaged": { "Date": "2026-10-09 21:08:53 UTC", "User": "root" }, "Author": "Mohammed Saqr [aut, cph] (ORCID:\n),\nSonsoles López-Pernas [aut, cre, cph] (ORCID:\n)", "Maintainer": "Sonsoles López-Pernas ", "_user": "mohsaqr", "_type": "src", "_file": "sbert_0.5.8.tar.gz", "_fileid": "https://r2.ropensci.org/0e8d5e2d632c38a765ea8e6854e30667cdc5a4b26d0d3140550aa63a2f8c60bc", "_filesize": 3117069, "_sha256": "0e8d5e2d632c38a765ea8e6854e30667cdc5a4b26d0d3140550aa63a2f8c60bc", "_expires": "2027-01-17T21:12:07.000Z", "_created": "2026-10-09T21:08:53.000Z", "_published": "2026-10-09T21:12:09.292Z", "_buildurl": "https://github.com/r-universe/mohsaqr/actions/runs/37991208536", "_status": "success", "_host": "GitHub-Actions", "_jobs": [ { "job": 114027146378, "time": 140, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "11645482327" }, { "job": 114027146411, "time": 132, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "11645830171" }, { "job": 114027146370, "time": 107, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "11645960026" }, { "job": 114027146295, "time": 95, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "11645850092" }, { "job": 114025626687, "time": 248, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "11645093496" }, { "job": 114027146307, "time": 115, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "11644779119" }, { "job": 114027146485, "time": 74, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "11644958767" }, { "job": 114027146547, "time": 100, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "11644938929" }, { "job": 114027146448, "time": 96, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "11645457376" } ], "_upstream": "https://github.com/sonsoleslp/sbert", "_commit": { "id": "387023d12ebc6cc73b8a32332fcc60c56ad79af7", "author": "Sonsoles López Pernas ", "committer": "Sonsoles López Pernas ", "message": "Fix pkgdown article\n", "time": 1791565404 }, "_maintainer": { "name": "Sonsoles López-Pernas", "email": "sonsoles.lopez@uef.fi", "login": "sonsoleslp", "twitter": "@sonsoleslp", "description": "Researcher at UPM", "uuid": 10948559, "orcid": "0000-0002-9621-1392" }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1.0", "role": "Depends" }, { "package": "digest", "role": "Imports" }, { "package": "grDevices", "role": "Imports" }, { "package": "graphics", "role": "Imports" }, { "package": "onnxr", "version": ">= 0.1.2", "role": "Imports" }, { "package": "parallel", "role": "Imports" }, { "package": "tok", "version": ">= 0.2.3", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "tools", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "SnowballC", "role": "Suggests" }, { "package": "jsonlite", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "withr", "role": "Suggests" } ], "_owner": "sonsoleslp", "_selfowned": false, "_usedby": 0, "_updates": [ { "week": "2026-31", "n": 2 }, { "week": "2026-32", "n": 9 }, { "week": "2026-33", "n": 3 }, { "week": "2026-34", "n": 4 }, { "week": "2026-36", "n": 2 }, { "week": "2026-40", "n": 7 }, { "week": "2026-41", "n": 6 } ], "_tags": [], "_topics": [ "bert", "embeddings", "nlp", "onnx", "sentence-embeddings", "sentence-transformers", "topic-modeling" ], "_stars": 0, "_contributors": [ { "user": "mohsaqr", "count": 20, "uuid": 194697827 }, { "user": "sonsoleslp", "count": 13, "uuid": 10948559 } ], "_userbio": { "uuid": 194697827, "type": "user", "name": "Mohammed Saqr", "followers": 14, "description": "Professor of Computer Science" }, "_downloads": { "count": 0, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/sbert" }, "_devurl": "https://github.com/sonsoleslp/sbert", "_pkgdown": "https://sonsoles.me/sbert/", "_searchresults": 0, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/sbert.html", "LICENSE" ], "_cranurl": false, "_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" ], "_datasets": [ { "name": "covid", "title": "COVID-19 Research Abstracts", "object": "covid", "class": [ "data.frame" ], "fields": [ "Year", "Abstract" ], "rows": 4170, "table": true, "tojson": true }, { "name": "feedback_translations", "title": "AI-generated Mathematics Feedback with English Translations", "object": "feedback_translations", "class": [ "data.frame" ], "fields": [ "feedback", "translation" ], "rows": 8757, "table": true, "tojson": true } ], "_help": [ { "page": "abbreviations", "title": "Obtain the Built-in Abbreviation Gazetteer", "topics": [ "abbreviations" ] }, { "page": "as.data.frame.sbert_topic_sweep", "title": "Coerce a Topic-Count Comparison to a Data Frame", "topics": [ "as.data.frame.sbert_topic_sweep" ] }, { "page": "blend", "title": "Blend Segment Embeddings with Their Document Context", "topics": [ "blend" ] }, { "page": "cache_dir", "title": "Locate the sbert Model Cache", "topics": [ "cache_dir" ] }, { "page": "cache_size", "title": "Measure the sbert Cache", "topics": [ "cache_size" ] }, { "page": "clean_corpus", "title": "Clean a Text Corpus Before Encoding", "topics": [ "clean_corpus" ] }, { "page": "coherence", "title": "Score Topic Coherence", "topics": [ "coherence" ] }, { "page": "compare_topics", "title": "Compare Topic Counts Before Committing to One", "topics": [ "compare_topics" ] }, { "page": "content_ratio", "title": "Alphabetic Content Ratio of Text", "topics": [ "content_ratio" ] }, { "page": "covid", "title": "COVID-19 Research Abstracts", "topics": [ "covid" ] }, { "page": "dedupe", "title": "Deduplicate a Text Corpus with Frequencies", "topics": [ "dedupe" ] }, { "page": "encode", "title": "Encode Text with Sentence-BERT", "topics": [ "encode" ] }, { "page": "feedback_translations", "title": "AI-generated Mathematics Feedback with English Translations", "topics": [ "feedback_translations" ] }, { "page": "fitted.sbert_topic_sweep", "title": "Extract One Fitted Model from a Topic-Count Comparison", "topics": [ "fitted.sbert_topic_sweep" ] }, { "page": "install_runtime", "title": "Install ONNX Runtime", "topics": [ "install_runtime" ] }, { "page": "keywords", "title": "Extract Keywords from Documents by Embedding Similarity", "topics": [ "keywords" ] }, { "page": "load_custom", "title": "Load an Arbitrary Hugging Face Embedding Model", "topics": [ "load_custom" ] }, { "page": "load_model", "title": "Load a Pinned Sentence-BERT Model", "topics": [ "load_model" ] }, { "page": "model_download", "title": "Download a Pinned Sentence-BERT Model", "topics": [ "model_download" ] }, { "page": "model_remove", "title": "Remove an Installed Model from the Cache", "topics": [ "model_remove" ] }, { "page": "model_status", "title": "Inspect an Installed Model", "topics": [ "model_status" ] }, { "page": "models", "title": "List the Available Pinned Sentence-BERT Models", "topics": [ "models" ] }, { "page": "plot.sbert_topic_hierarchy", "title": "Plot a Topic Hierarchy Dendrogram", "topics": [ "plot.sbert_topic_hierarchy" ] }, { "page": "plot.sbert_topic_model", "title": "Plot a Semantic Topic Model", "topics": [ "plot.sbert_topic_model" ] }, { "page": "plot.sbert_topic_sweep", "title": "Plot a Topic-Count Comparison", "topics": [ "plot.sbert_topic_sweep" ] }, { "page": "pool", "title": "Pool Token Embeddings into Sentence Embeddings", "topics": [ "pool" ] }, { "page": "predict.sbert_topic_model", "title": "Assign New Documents to Fitted Topics", "topics": [ "predict.sbert_topic_model" ] }, { "page": "print.sbert_model", "title": "Print a Loaded Model", "topics": [ "print.sbert_model" ] }, { "page": "print.sbert_topic_corpus", "title": "Print a Prepared Topic Corpus", "topics": [ "print.sbert_topic_corpus" ] }, { "page": "print.sbert_topic_hierarchy", "title": "Print a Topic Hierarchy", "topics": [ "print.sbert_topic_hierarchy" ] }, { "page": "print.sbert_topic_model", "title": "Print a Semantic Topic Model", "topics": [ "print.sbert_topic_model" ] }, { "page": "print.sbert_topic_sweep", "title": "Print a Topic-Count Comparison", "topics": [ "print.sbert_topic_sweep" ] }, { "page": "reduce_topics", "title": "Reduce a Fitted Topic Model to Fewer Topics", "topics": [ "reduce_topics" ] }, { "page": "representatives", "title": "Representative Text Units for Every Topic", "topics": [ "representatives" ] }, { "page": "segment", "title": "Segment Text into Sentences, Clauses, or Phrases", "topics": [ "segment" ] }, { "page": "stop_words", "title": "Obtain and Adjust the Topic Stop-Word List", "topics": [ "stop_words" ] }, { "page": "strip_list_markers", "title": "Strip Enumeration and List Markers from Text", "topics": [ "strip_list_markers" ] }, { "page": "summary.sbert_topic_model", "title": "Summarize a Semantic Topic Model", "topics": [ "summary.sbert_topic_model" ] }, { "page": "terms.sbert_topic_model", "title": "Topic Terms, Retuned Without Refitting", "topics": [ "terms.sbert_topic_model" ] }, { "page": "topic_corpus", "title": "Prepare a Corpus Once to Fit Many Topic Models", "topics": [ "topic_corpus" ] }, { "page": "topic_diversity", "title": "Measure Topic Diversity", "topics": [ "topic_diversity" ] }, { "page": "topic_gamma", "title": "Document-Topic Distributions from Segment Assignments", "topics": [ "topic_gamma" ] }, { "page": "topic_hierarchy", "title": "Build the Topic Hierarchy of a Fitted Model", "topics": [ "topic_hierarchy" ] }, { "page": "topic_membership", "title": "Soft Topic Membership Probabilities", "topics": [ "topic_membership" ] }, { "page": "topic_palette", "title": "Qualitative Colour Palette for Topics", "topics": [ "topic_palette" ] }, { "page": "topic_similarity", "title": "Compute Cosine Similarity", "topics": [ "topic_similarity" ] }, { "page": "topic_sizes", "title": "Topic Sizes on the Distinct and Weighted Scales", "topics": [ "topic_sizes" ] }, { "page": "topics", "title": "Discover Semantic Topics in Documents", "topics": [ "topics" ] } ], "_pkglogo": "https://github.com/sonsoleslp/sbert/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/sonsoleslp/sbert/raw/HEAD/README.md", "_rundeps": [ "cli", "cpp11", "digest", "onnxr", "R6", "tok" ], "_vignettes": [ { "source": "math_vignette.Rmd", "filename": "math_vignette.html", "title": "Semantic Topics in AI-Powered Mathematics Feedback", "engine": "knitr::rmarkdown", "headings": [ "Why this tutorial", "The corpus, deduplicated", "Choosing the number of topics", "Should you trust these topics?", "Size on two scales", "Two keyword views, one topic", "The topics at a glance", "Where to go from here" ], "created": "2026-09-28 12:45:47", "modified": "2026-10-09 17:03:24", "commits": 3 } ], "_score": 3.5440680443502757, "_indexed": false, "_nocasepkg": "sbert", "_universes": [ "mohsaqr" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.5.8", "date": "2026-10-09T21:11:03.000Z", "distro": "resolute", "commit": "387023d12ebc6cc73b8a32332fcc60c56ad79af7", "fileid": "https://r2.ropensci.org/decf5a75fc9e9345a0e390df2cb406e661a9d2b41822e34fbcdaedfb8c47161c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mohsaqr/actions/runs/37991208536" }, { "r": "4.6.1", "os": "linux", "version": "0.5.8", "date": "2026-10-09T21:10:58.000Z", "distro": "resolute", "commit": "387023d12ebc6cc73b8a32332fcc60c56ad79af7", "fileid": "https://r2.ropensci.org/a596800fd0dc54683b589e861fff559cfe735608e76e4667aef3dadb81651ed4", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mohsaqr/actions/runs/37991208536" }, { "r": "4.5.3", "os": "mac", "version": "0.5.8", "date": "2026-10-09T21:10:41.000Z", "commit": "387023d12ebc6cc73b8a32332fcc60c56ad79af7", "fileid": "https://r2.ropensci.org/db62718a639317c175b13e3d6894d3eb3b500aa8a9387bedca68859ed0403442", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mohsaqr/actions/runs/37991208536" }, { "r": "4.6.1", "os": "mac", "version": "0.5.8", "date": "2026-10-09T21:10:33.000Z", "commit": "387023d12ebc6cc73b8a32332fcc60c56ad79af7", "fileid": "https://r2.ropensci.org/871fc341cfafcefe131967946d417c36f403b947c04e70fb8f4c535072fdab08", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mohsaqr/actions/runs/37991208536" }, { "r": "4.6.0", "os": "wasm", "version": "0.5.8", "date": "2026-10-09T21:11:04.000Z", "commit": "387023d12ebc6cc73b8a32332fcc60c56ad79af7", "fileid": "https://r2.ropensci.org/a3366c694bce9f38baefb7e417dd0671e23b4c5dce72dd81ab7d40a0ef6cc259", "status": "success", "buildurl": "https://github.com/r-universe/mohsaqr/actions/runs/37991208536" }, { "r": "4.7.0", "os": "win", "version": "0.5.8", "date": "2026-10-09T21:09:59.000Z", "commit": "387023d12ebc6cc73b8a32332fcc60c56ad79af7", "fileid": "https://r2.ropensci.org/ceca20db82818b568ac578ae779262c381122e2955874488ed1fecffebe66142", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mohsaqr/actions/runs/37991208536" }, { "r": "4.5.3", "os": "win", "version": "0.5.8", "date": "2026-10-09T21:10:13.000Z", "commit": "387023d12ebc6cc73b8a32332fcc60c56ad79af7", "fileid": "https://r2.ropensci.org/c7dac49c9d57a5ec95e940c4001e74471384e3684292e156cc2b2049b0077b8e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mohsaqr/actions/runs/37991208536" }, { "r": "4.6.1", "os": "win", "version": "0.5.8", "date": "2026-10-09T21:10:05.000Z", "commit": "387023d12ebc6cc73b8a32332fcc60c56ad79af7", "fileid": "https://r2.ropensci.org/57bd04b7212c37d7b1b66f93ec4660dc0949574523e26567b8c9edaffab75adc", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/mohsaqr/actions/runs/37991208536" } ] }