2c:null 2d:["$","title",null,{"children":"Feature Analysis in RiTa | Daniel Howe | Observable"}] 32:T407,html`

Related Resources

The RiTa reference in observable
The RiTa website: examples, docs, gallery, etc.
A tutorial on RiScript, RiTa's simple scripting language
Tools for RiTa in observable, including the rs template
Generating with RiTa grammars and Markov chains
Using RiScript and RiTa Grammars within Twine

`33:T841,html`

function	description
search()	full/partial match on any combination of features
randomWord()	fetch word matching any combination of features
rhymes()	rhyming algorithm uses phoneme/syllable features
spellsLike()	comparison of letters via min-edit-distance
soundsLike()	comparison of phonemes via min-edit-distance
alliterations()	algorithm uses phoneme/syllable features

`34:[{"id":"5ad1543f837d40bf1e53e53aed49c6130d630660020409c1b8667bdba391951d629d12003864064f1c31034230eb893315f9d46b9d325922eda0ebfdfa1bbd38","href":"https://static.observableusercontent.com/files/5ad1543f837d40bf1e53e53aed49c6130d630660020409c1b8667bdba391951d629d12003864064f1c31034230eb893315f9d46b9d325922eda0ebfdfa1bbd38","name":"RiTa.png","type":"image/png","lastModified":1621426534193.057,"size":26700}] 30:{"id":"192b882327f33508","slug":"rita-lexicon","title":"Feature Analysis in RiTa","thumbnail":"ae5ab5716f9c0fa6b815f963a1b868c4165cea0d7bd3b1267d8ed289600c99cc","access_level":"public","create_time":"$D2021-05-19T12:12:29.493Z","update_time":"$D2024-04-09T06:52:05.068Z","view_time":null,"first_public_time":"$D2021-05-21T11:09:27.796Z","has_unpublished_edits":null,"fork":false,"stars":4,"starred":false,"owner":{"type":"team","id":"636cf123a07db681","login":"dhowe","name":"Daniel Howe","avatar_url":"https://avatars-next.observableusercontent.com/a5081aaa56ae9990aa27642040dc61de3ce8cea67f6f778a5b864e41111ba7a3","tier":"starter_2024"},"version":728,"publish_version":null,"role":null,"authored":false,"authors":[{"type":"individual","id":"32869872eb6f2f82","login":"dhowe","name":"Daniel Howe","avatar_url":"https://avatars-next.observableusercontent.com/a5081aaa56ae9990aa27642040dc61de3ce8cea67f6f778a5b864e41111ba7a3","tier":null}],"members":[{"type":"individual","id":"32869872eb6f2f82","login":"dhowe","name":"Daniel Howe","avatar_url":"https://avatars-next.observableusercontent.com/a5081aaa56ae9990aa27642040dc61de3ce8cea67f6f778a5b864e41111ba7a3","tier":null,"role":"editor"}],"comments":[],"custom_thumbnail":true,"trashed":false,"lapsed":null,"subscribed":null,"forks":6,"collection":{"id":"3c04483074fcc200","slug":"rita","title":"RiTa","owner":{"id":"636cf123a07db681","login":"dhowe","name":"Daniel Howe"}},"type":"notebook","body":{"titling":"auto","title":"Feature Analysis in RiTa","cells":[{"id":0,"value":"md`# Feature Analysis in RiTa

RiTa: tools for generative natural language

\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":327,"value":"$32","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":265,"value":"md`RiTa includes two components that allow it to analyze, and search on, language features such as meter, rhyme, phonemes, syllables, or part-of-speech. These components, the lexicon and letter-to-sound (or LTS) engine, work together to provide data for known and unknown words.\n\nThe lexicon provides pronunciation and part-of-speech data for common words (including irregulars), while the LTS-engine derives the data for regular forms of these roots, as well as for words not found in the lexicon. Part-of-speech tagging integrates both components, as initial tags are assigned via the lexicon, then refined, based on context, via rules in the engine. \n

\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":3,"value":"md`\n## The Lexicon\nRiTa includes a user-customisable lexicon containing pronunciation and part-of-speech data for the root forms of approximately 25,000 of the most common English words¹. \n

\nThe lexicon can be searched via partial, full or regex matches on abitrary combinations of features including spelling, phonemes, stresses, and syllables, part-of-speech, word-length and syllable-count. It can also be used, via the _randomWord()_, function to find a word that matches a particular set of criteria.\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":79,"value":"$33","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":110,"value":"md`¹To minimize space, inflections (plurals, verb forms, etc.) are constructed algorithmically as needed. The uncompressed lexicon is about 900k in size.
`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":335,"value":"md`\n## Letter-to-Sound (LTS) Engine\nRiTa's Letter-to-Sound engine, based-upon the one developed for FreeTTS, allows for feature analysis of arbitrary words. It works by breaking down words into sounds (phonemes) rather than spellings, which allows it to match, for example, words with similar pronunciation but different spellings. \n\nUsing a phonemic representation we can analyze the similarity between the sounds of words or, as the engine outputs stress patterns, we can test and generate things like alliteration, rhyme and meter. RiTa's LTS-engine also provides inflection (pluralization, conjugation, etc.) for regular and irregular forms of words in the lexicon.\n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":219,"value":"md`-------------\n## Some examples using feature analysis in RiTa`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":124,"value":"html` \n`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":407,"value":"md`See complete examples here...`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"}],"files":"$W34","stdlib":"1"}} 31:"$30:body"