#No training, no prolog. a Natural-Language-Processing library in Javascript, small-enough for the browser, and quick-enough to run on keypress 👬
it does tons of clever things. it's smaller than jquery, and scores 86% on the Penn treebank.
nlp.pos('she sells seashells by the seashore').to_past().text()
//she sold seashells by the seashore
##Justification If the 80-20 rule applies for most things, the ''94-6 rule'' applies when working with language - by Zipfs law:
The top 10 words account for 25% of used language.
The top 100 words account for 50% of used language.
The top 50,000 words account for 95% of used language.
On the Penn treebank, for example, this is possible:
- just a 1 thousand word lexicon: 45% accuracy
- ... then falling back to nouns: 70% accuracy
- ... then some suffix regexes: 74% accuracy
- ... then some sentence-level postprocessing: 81% accuracy
The process is to get some curated data, find the patterns, and list the exceptions. Bada bing, bada boom. In this way a satisfactory NLP library can be built with breathtaking lightness.
Namely, it can be run right on the user's computer instead of a server.
<script src="https://rawgit.com/spencermountain/nlp_compromise/master/client_side/nlp.min.js"> </script>
<script>
nlp.noun("dinosaur").pluralize()
//dinosaurs
</script>or, use the angular module
$ npm install nlp_compromise
nlp = require("nlp_compromise")
nlp.syllables("hamburger")
//[ 'ham', 'bur', 'ger' ]###Sentence methods
var s= nlp.pos("they are lovers").sentences[0]
s.tense()
//present
s.text()
//"they are lovers"
s.to_past().text()
//they were lovers
s.to_present().text()
//the are lovers
s.to_future().text()
//they will be lovers
s.negate().text()
//they are not lovers
s.tags()
//[ 'PRP', 'CP', 'JJ' ]
s.nouns()
s.adjectives()
s.adverbs()
s.verbs()
s.values()###Noun methods:
nlp.noun("earthquakes").singularize()
//earthquake
nlp.noun("earthquake").pluralize()
//earthquakes
nlp.noun('veggie burger').is_plural
//false
nlp.noun('hour').article()
//an
nlp.inflect('mayors of toronto'))
//{ plural: 'mayors of toronto', singular: 'mayor of toronto' }###Verb methods:
nlp.verb("walked").conjugate()
//{ infinitive: 'walk',
// present: 'walks',
// past: 'walked',
// gerund: 'walking'}
nlp.verb('swimming').to_past()
//swam###Adjective methods:
nlp.adjective("quick").conjugate()
// { comparative: 'quicker',
// superlative: 'quickest',
// adverb: 'quickly',
// noun: 'quickness'}###Adverb methods
nlp.adverb("quickly").conjugate()
// { adjective: 'quick'}86% on the Penn treebank
nlp.pos("Tony Hawk walked quickly to the store.").tags()
// [ [ 'NN', 'VB', 'RB', 'IN', 'DT', 'NN' ] ]
nlp.pos("they would swim").tags()
// [ [ 'PRP', 'MD', 'VBP' ] ]
nlp.pos("the obviously good swim").tags()
// [ [ 'DT', 'RB', 'JJ', 'NN' ] ]nlp.spot("Tony Hawk walked quickly to the store.")
// ["Tony Hawk", "store"]
nlp.spot("joe carter loves toronto")
// ["joe carter", "toronto"]nlp.sentences("Hi Dr. Miller the price is 4.59 for the U.C.L.A. Ph.Ds.").length
//1
nlp.tokenize("she sells sea-shells").length
//370% on the moby hyphenization corpus 0.5k
nlp.syllables("hamburger")
//[ 'ham', 'bur', 'ger' ]nlp.americanize("favourite")
//favorite
nlp.britishize("synthesized")
//synthesisedstr= "She sells seashells by the seashore. The shells she sells are surely seashells."
nlp.ngram(str, {min_count:1, max_size:5})
// [{ word: 'she sells', count: 2, size: 2 },
// ...
options.min_count // throws away seldom-repeated grams. defaults to 1
options.max_gram // prevents the result from becoming gigantic. defaults to 5a hugely-ignorant, and widely subjective transliteration of latin, cryllic, greek unicode characters to english ascii.
nlp.normalize("Björk")
//Bjorkand for fun,
nlp.denormalize("The quick brown fox jumps over the lazy dog", {percentage:50})
// The ɋӈїck brown fox juӎÞs over tӊe laζy dog "verb":
"VB" : "verb, generic (eat)"
"VBD" : "past-tense verb (ate)"
"VBN" : "past-participle verb (eaten)"
"VBP" : "infinitive verb (eat)"
"VBZ" : "present-tense verb (eats, swims)"
"CP" : "copula (is, was, were)"
"VBG" : "gerund verb (eating,winning)"
"adjective":
"JJ" : "adjective, generic (big, nice)"
"JJR" : "comparative adjective (bigger, cooler)"
"JJS" : "superlative adjective (biggest, fattest)"
"adverb":
"RB" : "adverb (quickly, softly)"
"RBR" : "comparative adverb (faster, cooler)"
"RBS" : "superlative adverb (fastest (driving), coolest (looking))"
"noun":
"NN" : "noun, singular (dog, rain)"
"NNP" : "singular proper noun (Edinburgh, skateboard)"
"NNPS" : "plural proper noun (Smiths)"
"NNS" : "plural noun (dogs, foxes)"
"NNO" : "possessive noun (spencer's, sam's)"
"NG" : "gerund noun (eating,winning" : "but used grammatically as a noun)"
"PRP" : "personal pronoun (I,you,she)"
"glue":
"PP" : "possessive pronoun (my,one's)"
"FW" : "foreign word (mon dieu, voila)"
"IN" : "preposition (of,in,by)"
"MD" : "modal verb (can,should)"
"CC" : "co-ordating conjunction (and,but,or)"
"DT" : "determiner (the,some)"
"UH" : "interjection (oh, oops)"
"EX" : "existential there (there)"
"value":
"CD" : "cardinal value, generic (one, two, june 5th)"
"DA" : "date (june 5th, 1998)"
"NU" : "number (89, half-million)"####Lexicon Because the library can conjugate all sorts of forms, it only needs to store one grammatical form. The lexicon was built using the American National Corpus, then intersected with the regex rule-list. For example, it lists only 300 verbs, then blasts-out their 1200+ derived forms.
####Contractions Unlike other nlp toolkits, this library puts a 'silent token' into the phrase for contractions. Otherwise something would be neglected.
nlp.pos("i'm good.")
[{
text:"i'm",
normalised:"i",
pos:"PRP"
},
{
text:"",
normalised:"am",
pos:"CP"
},
{
text:"good.",
normalised:"good",
pos:"JJ"
}]####Tokenization Neighbouring words with the same part of speech are merged together, unless there is punctuation, different capitalisation, or special cases.
nlp.pos("tony hawk won")
//tony hawk NN
//won VBTo turn this off:
nlp.pos("tony hawk won", {dont_combine:true})
//tony NN
//hawk NN
//won VBMIT
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent