Topic Modeling with 'Sentence-BERT' Embeddings


[Up] [Top]

Documentation for package ‘sbert’ version 0.6.0

Help Pages

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