| sbert-package | sbert: Topic modeling with Sentence-BERT embeddings |
| abbreviations | List the abbreviations protected from sentence splitting |
| as.data.frame.sbert_topic_corpus | Convert a prepared topic corpus to a data frame |
| as.data.frame.sbert_topic_hierarchy | Convert a topic hierarchy to a data frame |
| as.data.frame.sbert_topic_model | Convert a topic model to a data frame |
| as.data.frame.sbert_topic_sweep | Convert a topic-count comparison to a data frame |
| blend | Blend segment embeddings with their document context |
| cache_dir | Locate the model cache |
| cache_size | Measure the disk space of the model cache |
| clean_corpus | Clean a corpus before encoding |
| coherence | Score the coherence of topics |
| compare_topics | Compare numbers of topics and segmentation levels |
| content_ratio | Compute the share of letters in text |
| covid | COVID-19 research abstracts |
| dedupe | Collapse repeated texts and count them |
| encode | Encode texts as sentence embeddings |
| feedback_embeddings | Precomputed embeddings of 600 feedback messages |
| feedback_translations | AI-generated mathematics feedback with English translations |
| fitted.sbert_topic_sweep | Extract a fitted model from a topic-count comparison |
| install_runtime | Install ONNX Runtime |
| keywords | Extract the keywords of documents |
| load_custom | Load a Hugging Face embedding model outside the pinned list |
| load_model | Load an installed pinned model |
| models | List the pinned models |
| model_download | Download a pinned model |
| model_remove | Remove a pinned model from the cache |
| model_status | Check the installed files of a model |
| name_topics | Name the topics of a fitted model |
| plot.sbert_topic_hierarchy | Plot a topic hierarchy as a dendrogram |
| plot.sbert_topic_model | Plot a fitted topic model |
| plot.sbert_topic_sweep | Plot a topic-count comparison |
| pool | Pool token embeddings into sentence embeddings |
| predict.sbert_topic_model | Assign new documents to fitted topics |
| print.sbert_model | Print a loaded model |
| print.sbert_topic_corpus | Print a prepared topic corpus |
| print.sbert_topic_hierarchy | Print a topic hierarchy |
| print.sbert_topic_model | Print a topic model |
| print.sbert_topic_sweep | Print a topic-count comparison |
| print.summary.sbert_topic_hierarchy | Print a topic hierarchy summary |
| print.summary.sbert_topic_model | Print a topic model summary |
| print.summary.sbert_topic_sweep | Print a topic-count comparison summary |
| reduce_topics | Merge the topics of a model into fewer topics |
| representatives | Select representative texts for each topic |
| sbert | sbert: Topic modeling with Sentence-BERT embeddings |
| segment | Split documents into sentences, clauses, or phrases |
| stop_words | Get and adjust the stop-word list |
| strip_list_markers | Remove list and enumeration markers from text |
| summary.sbert_topic_hierarchy | Summarize a topic hierarchy |
| summary.sbert_topic_model | Summarize a topic model |
| summary.sbert_topic_sweep | Summarize a topic-count comparison |
| terms.sbert_topic_model | Compute the terms of each topic |
| topics | Fit semantic topics to documents |
| topic_corpus | Prepare a corpus once for several topic models |
| topic_diversity | Measure the diversity of topic terms |
| topic_gamma | Compute document-topic mixtures from segments |
| topic_hierarchy | Build the hierarchy of the topics of a model |
| topic_membership | Compute graded topic membership |
| topic_palette | Get colors that distinguish topics in plots |
| topic_similarity | Compute cosine similarity between embeddings |
| topic_sizes | Compute the size of each topic |