fastTextWordEmbedding — Return a compact fastText-style word embedding compatibility model.
fastTextWordEmbedding returns a RunMat wordEmbedding compatibility object with Dimension 300 and a compact built-in English vocabulary.
Syntax
emb = fastTextWordEmbeddingReturns
| Name | Type | Description |
|---|---|---|
emb | Any | Word embedding compatibility object. |
Errors
| Identifier | When | Message |
|---|---|---|
RunMat:fastTextWordEmbedding:InvalidInput | Inputs do not match the supported fastTextWordEmbedding form. | fastTextWordEmbedding received invalid input |
How fastTextWordEmbedding works
- The supported form is the zero-argument
emb = fastTextWordEmbeddingform. - The returned object exposes
DimensionandVocabularyand stores dense vectors in the same implementation-detail property used byword2vec,vec2word, anddoc2sequence. - The compact model includes curated vectors for common examples such as
Italy - Rome + Paris, which maps back toFrancewithvec2word. - RunMat does not download MathWorks support packages. The full 1-million-word fastText English 16 Billion Token model remains tracked in the broader Text Analytics compatibility issue.
GPU memory and residency
fastTextWordEmbedding performs host object construction and has no provider kernel.
Examples
Create The Compatibility Model
emb = fastTextWordEmbeddingExpected output:
`emb.Dimension` is 300.Use With Embedding Lookup
italy = word2vec(emb,"Italy");
rome = word2vec(emb,"Rome");
paris = word2vec(emb,"Paris");
word = vec2word(emb, italy - rome + paris)Expected output:
`word` is `"France"` for the bundled compact model.Using fastTextWordEmbedding with coding agents
Open a RunMat example with live inputs, then ask the agent to explain how fastTextWordEmbedding changes the result.
Run a small fastTextWordEmbedding example, explain the result, then change one input and compare the output.
FAQ
Does this include MATLAB's full pretrained fastText support-package corpus?⌄
No. RunMat currently provides a compact compatibility model so scripts can construct and use a wordEmbedding object. Full support-package corpus parity remains open.
Can the result be used with word2vec, vec2word, and doc2sequence?⌄
Yes. The returned object uses the same RunMat wordEmbedding representation as readWordEmbedding and trainWordEmbedding.
Does fastTextWordEmbedding execute on the GPU?⌄
No. It constructs host text/model metadata and dense vectors.
Related Strings functions
Text Analytics
addDependencyDetails · addEntityDetails · addLemmaDetails · addPartOfSpeechDetails · addSentenceDetails · addTypeDetails · bagOfNgrams · bagOfWords · cosineSimilarity · doc2sequence · encode · extractFileText · extractHTMLText · findElement · getAttribute · htmlTree · ind2word · isVocabularyWord · normalizeWords · readWordEmbedding · removeLongWords · removeShortWords · removeStopWords · removeWords · stopWords · tokenDetails · tokenizedDocument · trainWordEmbedding · vaderSentimentScores · vec2word · word2ind · word2vec · wordEncoding · writeWordEmbedding
Transform
append · deblank · erase · eraseBetween · erasePunctuation · eraseURLs · extractAfter · extractBefore · extractBetween · insertAfter · insertBefore · join · lower · pad · replace · replaceBetween · reverse · split · splitlines · strcat · strip · strjoin · strjust · strrep · strsplit · strtrim · upper
Core
blanks · char · compose · convertCharsToStrings · convertContainedStringsToChars · convertStringsToChars · genvarname · int2str · isletter · isspace · isStringScalar · isstrprop · mat2str · native2unicode · newline · num2str · sprintf · sscanf · str2double · str2num · strcmp · strcmpi · string · string.empty · strings · strlength · strncmp · strncmpi · strtok · unicode2native
Search
contains · endsWith · matches · startsWith · strfind
Pattern
digitsPattern · lettersPattern · pattern · regexpPattern · textBoundary · wildcardPattern
Open-source implementation
Unlike proprietary runtimes, every RunMat function is open-source. Read exactly how fastTextWordEmbedding is executed, line by line, in Rust.
- View the source for fastTextWordEmbedding in Rust on GitHub
- Learn how the RunMat runtime works
- Found a bug? Open an issue with a minimal reproduction.
About RunMat
RunMat is an open-source runtime that executes MATLAB-syntax code blazing on any GPU. It is licensed under the Apache 2.0 license.
- RunMat automatically optimizes your math for GPU execution on Apple, Nvidia, and AMD hardware. No code changes needed. Simulations that took hours now take minutes.
- Start running code in seconds. RunMat runs in the browser, on the desktop, or from the CLI. No license server, no IT ticket.